korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-27 14:14:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

arm64 updates for 6.3:

Browse Source 
- Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit
   architectural register (ZT0, for the look-up table feature) that Linux
   needs to save/restore.
 
 - Include TPIDR2 in the signal context and add the corresponding
   kselftests.
 
 - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI
   support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG
   (ARM CMN) at probe time.
 
 - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64.
 
 - Permit EFI boot with MMU and caches on. Instead of cleaning the entire
   loaded kernel image to the PoC and disabling the MMU and caches before
   branching to the kernel bare metal entry point, leave the MMU and
   caches enabled and rely on EFI's cacheable 1:1 mapping of all of
   system RAM to populate the initial page tables.
 
 - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64
   kernel (the arm32 kernel only defines the values).
 
 - Harden the arm64 shadow call stack pointer handling: stash the shadow
   stack pointer in the task struct on interrupt, load it directly from
   this structure.
 
 - Signal handling cleanups to remove redundant validation of size
   information and avoid reading the same data from userspace twice.
 
 - Refactor the hwcap macros to make use of the automatically generated
   ID registers. It should make new hwcaps writing less error prone.
 
 - Further arm64 sysreg conversion and some fixes.
 
 - arm64 kselftest fixes and improvements.
 
 - Pointer authentication cleanups: don't sign leaf functions, unify
   asm-arch manipulation.
 
 - Pseudo-NMI code generation optimisations.
 
 - Minor fixes for SME and TPIDR2 handling.
 
 - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable, replace
   strtobool() to kstrtobool() in the cpufeature.c code, apply dynamic
   shadow call stack in two passes, intercept pfn changes in set_pte_at()
   without the required break-before-make sequence, attempt to dump all
   instructions on unhandled kernel faults.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE5RElWfyWxS+3PLO2a9axLQDIXvEFAmP0/QsACgkQa9axLQDI
 XvG+gA/+JDVEH9wRzAIZvbp9hSuohPc48xgAmIMP1eiVB0/5qeRjYAJwS33H0rXS
 BPC2kj9IBy/eQeM9ICg0nFd0zYznSVacITqe6NrqeJ1F+ftS4rrHdfxd+J7kIoCs
 V2L8e+BJvmHdhmNV2qMAgJdGlfxfQBA7fv2cy52HKYcouoOh1AUVR/x+yXVXAsCd
 qJP3+dlUKccgm/oc5unEC1eZ49u8O+EoasqOyfG6K5udMgzhEX3K6imT9J3hw0WT
 UjstYkx5uGS/prUrRCQAX96VCHoZmzEDKtQuHkHvQXEYXsYPF3ldbR2CziNJnHe7
 QfSkjJlt8HAtExA+BkwEe9i0MQO/2VF5qsa2e4fA6l7uqGu3LOtS/jJd23C9n9fR
 Id8aBMeN6S8+MjqRA9L2uf4t6e4ISEHoG9ZRdc4WOwloxEEiJoIeun+7bHdOSZLj
 AFdHFCz4NXiiwC0UP0xPDI2YeCLqt5np7HmnrUqwzRpVO8UUagiJD8TIpcBSjBN9
 J68eidenHUW7/SlIeaMKE2lmo8AUEAJs9AorDSugF19/ThJcQdx7vT2UAZjeVB3j
 1dbbwajnlDOk/w8PQC4thFp5/MDlfst0htS3WRwa+vgkweE2EAdTU4hUZ8qEP7FQ
 smhYtlT1xUSTYDTqoaG/U2OWR6/UU79wP0jgcOsHXTuyYrtPI/Q=
 =VmXL
 -----END PGP SIGNATURE-----

Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit
   architectural register (ZT0, for the look-up table feature) that
   Linux needs to save/restore

 - Include TPIDR2 in the signal context and add the corresponding
   kselftests

 - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI
   support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG
   (ARM CMN) at probe time

 - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64

 - Permit EFI boot with MMU and caches on. Instead of cleaning the
   entire loaded kernel image to the PoC and disabling the MMU and
   caches before branching to the kernel bare metal entry point, leave
   the MMU and caches enabled and rely on EFI's cacheable 1:1 mapping of
   all of system RAM to populate the initial page tables

 - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64
   kernel (the arm32 kernel only defines the values)

 - Harden the arm64 shadow call stack pointer handling: stash the shadow
   stack pointer in the task struct on interrupt, load it directly from
   this structure

 - Signal handling cleanups to remove redundant validation of size
   information and avoid reading the same data from userspace twice

 - Refactor the hwcap macros to make use of the automatically generated
   ID registers. It should make new hwcaps writing less error prone

 - Further arm64 sysreg conversion and some fixes

 - arm64 kselftest fixes and improvements

 - Pointer authentication cleanups: don't sign leaf functions, unify
   asm-arch manipulation

 - Pseudo-NMI code generation optimisations

 - Minor fixes for SME and TPIDR2 handling

 - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable,
   replace strtobool() to kstrtobool() in the cpufeature.c code, apply
   dynamic shadow call stack in two passes, intercept pfn changes in
   set_pte_at() without the required break-before-make sequence, attempt
   to dump all instructions on unhandled kernel faults

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (130 commits)
  arm64: fix .idmap.text assertion for large kernels
  kselftest/arm64: Don't require FA64 for streaming SVE+ZA tests
  kselftest/arm64: Copy whole EXTRA context
  arm64: kprobes: Drop ID map text from kprobes blacklist
  perf: arm_spe: Print the version of SPE detected
  perf: arm_spe: Add support for SPEv1.2 inverted event filtering
  perf: Add perf_event_attr::config3
  arm64/sme: Fix __finalise_el2 SMEver check
  drivers/perf: fsl_imx8_ddr_perf: Remove set-but-not-used variable
  arm64/signal: Only read new data when parsing the ZT context
  arm64/signal: Only read new data when parsing the ZA context
  arm64/signal: Only read new data when parsing the SVE context
  arm64/signal: Avoid rereading context frame sizes
  arm64/signal: Make interface for restore_fpsimd_context() consistent
  arm64/signal: Remove redundant size validation from parse_user_sigframe()
  arm64/signal: Don't redundantly verify FPSIMD magic
  arm64/cpufeature: Use helper macros to specify hwcaps
  arm64/cpufeature: Always use symbolic name for feature value in hwcaps
  arm64/sysreg: Initial unsigned annotations for ID registers
  arm64/sysreg: Initial annotation of signed ID registers
  ...
This commit is contained in:
Linus Torvalds 2023-02-21 15:27:48 -08:00
commit 8bf1a529cd
121 changed files with 3643 additions and 1062 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
Documentation/arm64/booting.rst
View File

@ -223,7 +223,7 @@ Before jumping into the kernel, the following conditions must be met:
For systems with a GICv3 interrupt controller to be used in v3 mode:
- If EL3 is present:
- ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1.
- ICC_SRE_EL3.Enable (bit 3) must be initialised to 0b1.
- ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1.
- ICC_CTLR_EL3.PMHE (bit 6) must be set to the same value across
all CPUs the kernel is executing on, and must stay constant
@ -369,6 +369,16 @@ Before jumping into the kernel, the following conditions must be met:
- HCR_EL2.ATA (bit 56) must be initialised to 0b1.
For CPUs with the Scalable Matrix Extension version 2 (FEAT_SME2):
- If EL3 is present:
- SMCR_EL3.EZT0 (bit 30) must be initialised to 0b1.
- If the kernel is entered at EL1 and EL2 is present:
- SMCR_EL2.EZT0 (bit 30) must be initialised to 0b1.
The requirements described above for CPU mode, caches, MMUs, architected
timers, coherency and system registers apply to all CPUs. All CPUs must
enter the kernel in the same exception level. Where the values documented

20
Documentation/arm64/elf_hwcaps.rst
View File

@ -14,7 +14,7 @@ Some hardware or software features are only available on some CPU
implementations, and/or with certain kernel configurations, but have no
architected discovery mechanism available to userspace code at EL0. The
kernel exposes the presence of these features to userspace through a set
of flags called hwcaps, exposed in the auxilliary vector.
of flags called hwcaps, exposed in the auxiliary vector.
Userspace software can test for features by acquiring the AT_HWCAP or
AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant
@ -284,6 +284,24 @@ HWCAP2_RPRFM
HWCAP2_SVE2P1
Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0010.
HWCAP2_SME2
Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0001.
HWCAP2_SME2P1
Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0010.
HWCAP2_SMEI16I32
Functionality implied by ID_AA64SMFR0_EL1.I16I32 == 0b0101
HWCAP2_SMEBI32I32
Functionality implied by ID_AA64SMFR0_EL1.BI32I32 == 0b1
HWCAP2_SMEB16B16
Functionality implied by ID_AA64SMFR0_EL1.B16B16 == 0b1
HWCAP2_SMEF16F16
Functionality implied by ID_AA64SMFR0_EL1.F16F16 == 0b1
4. Unused AT_HWCAP bits
-----------------------

55
Documentation/arm64/sme.rst
View File

@ -18,14 +18,19 @@ model features for SME is included in Appendix A.
1. General
-----------
* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA
register state and TPIDR2_EL0 are tracked per thread.
* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA and (when
present) ZTn register state and TPIDR2_EL0 are tracked per thread.
* The presence of SME is reported to userspace via HWCAP2_SME in the aux vector
AT_HWCAP2 entry. Presence of this flag implies the presence of the SME
instructions and registers, and the Linux-specific system interfaces
described in this document. SME is reported in /proc/cpuinfo as "sme".
* The presence of SME2 is reported to userspace via HWCAP2_SME2 in the
aux vector AT_HWCAP2 entry. Presence of this flag implies the presence of
the SME2 instructions and ZT0, and the Linux-specific system interfaces
described in this document. SME2 is reported in /proc/cpuinfo as "sme2".
* Support for the execution of SME instructions in userspace can also be
detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS
instruction, and checking that the value of the SME field is nonzero. [3]
@ -44,6 +49,7 @@ model features for SME is included in Appendix A.
HWCAP2_SME_B16F32
HWCAP2_SME_F32F32
HWCAP2_SME_FA64
HWCAP2_SME2
This list may be extended over time as the SME architecture evolves.
@ -52,8 +58,8 @@ model features for SME is included in Appendix A.
cpu-feature-registers.txt for details.
* Debuggers should restrict themselves to interacting with the target via the
NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets. The recommended way
of detecting support for these regsets is to connect to a target process
NT_ARM_SVE, NT_ARM_SSVE, NT_ARM_ZA and NT_ARM_ZT regsets. The recommended
way of detecting support for these regsets is to connect to a target process
first and then attempt a
ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov).
@ -89,13 +95,13 @@ be zeroed.
-------------------------
* On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the
ZA matrix are preserved.
ZA matrix and ZTn (if present) are preserved.
* On syscall PSTATE.SM will be cleared and the SVE registers will be handled
as per the standard SVE ABI.
* Neither the SVE registers nor ZA are used to pass arguments to or receive
results from any syscall.
* None of the SVE registers, ZA or ZTn are used to pass arguments to
or receive results from any syscall.
* On process creation (eg, clone()) the newly created process will have
PSTATE.SM cleared.
@ -111,6 +117,9 @@ be zeroed.
* Signal handlers are invoked with streaming mode and ZA disabled.
* A new signal frame record TPIDR2_MAGIC is added formatted as a struct
tpidr2_context to allow access to TPIDR2_EL0 from signal handlers.
* A new signal frame record za_context encodes the ZA register contents on
signal delivery. [1]
@ -134,6 +143,14 @@ be zeroed.
__reserved[] referencing this space. za_context is then written in the
extra space. Refer to [1] for further details about this mechanism.
* If ZTn is supported and PSTATE.ZA==1 then a signal frame record for ZTn will
be generated.
* The signal record for ZTn has magic ZT_MAGIC (0x5a544e01) and consists of a
standard signal frame header followed by a struct zt_context specifying
the number of ZTn registers supported by the system, then zt_context.nregs
blocks of 64 bytes of data per register.
5. Signal return
-----------------
@ -151,6 +168,9 @@ When returning from a signal handler:
the signal frame does not match the current vector length, the signal return
attempt is treated as illegal, resulting in a forced SIGSEGV.
* If ZTn is not supported or PSTATE.ZA==0 then it is illegal to have a
signal frame record for ZTn, resulting in a forced SIGSEGV.
6. prctl extensions
--------------------
@ -214,8 +234,8 @@ prctl(PR_SME_SET_VL, unsigned long arg)
vector length that will be applied at the next execve() by the calling
thread.
* Changing the vector length causes all of ZA, P0..P15, FFR and all bits of
Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
* Changing the vector length causes all of ZA, ZTn, P0..P15, FFR and all
bits of Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
unspecified, including both streaming and non-streaming SVE state.
Calling PR_SME_SET_VL with vl equal to the thread's current vector
length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
@ -317,6 +337,15 @@ The regset data starts with struct user_za_header, containing:
* The effect of writing a partial, incomplete payload is unspecified.
* A new regset NT_ARM_ZT is defined for access to ZTn state via
PTRACE_GETREGSET and PTRACE_SETREGSET.
* The NT_ARM_ZT regset consists of a single 512 bit register.
* When PSTATE.ZA==0 reads of NT_ARM_ZT will report all bits of ZTn as 0.
* Writes to NT_ARM_ZT will set PSTATE.ZA to 1.
8. ELF coredump extensions
---------------------------
@ -331,6 +360,11 @@ The regset data starts with struct user_za_header, containing:
been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread
when the coredump was generated.
* A NT_ARM_ZT note will be added to each coredump for each thread of the
dumped process. The contents will be equivalent to the data that would have
been read if a PTRACE_GETREGSET of NT_ARM_ZT were executed for each thread
when the coredump was generated.
* The NT_ARM_TLS note will be extended to two registers, the second register
will contain TPIDR2_EL0 on systems that support SME and will be read as
zero with writes ignored otherwise.
@ -406,6 +440,9 @@ In A64 state, SME adds the following:
For best system performance it is strongly encouraged for software to enable
ZA only when it is actively being used.
* A new ZT0 register is introduced when SME2 is present. This is a 512 bit
register which is accessible when PSTATE.ZA is set, as ZA itself is.
* Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and
SMSTOP instructions or by access to the SVCR system register:

4
Documentation/arm64/sve.rst
View File

@ -175,7 +175,7 @@ the SVE instruction set architecture.
When returning from a signal handler:
* If there is no sve_context record in the signal frame, or if the record is
present but contains no register data as desribed in the previous section,
present but contains no register data as described in the previous section,
then the SVE registers/bits become non-live and take unspecified values.
* If sve_context is present in the signal frame and contains full register
@ -223,7 +223,7 @@ prctl(PR_SVE_SET_VL, unsigned long arg)
Defer the requested vector length change until the next execve()
performed by this thread.
The effect is equivalent to implicit exceution of the following
The effect is equivalent to implicit execution of the following
call immediately after the next execve() (if any) by the thread:
prctl(PR_SVE_SET_VL, arg & ~PR_SVE_SET_VL_ONEXEC)

5
arch/arm/include/asm/arch_gicv3.h
View File

@ -252,5 +252,10 @@ static inline void gic_arch_enable_irqs(void)
WARN_ON_ONCE(true);
}
static inline bool gic_has_relaxed_pmr_sync(void)
{
return false;
}
#endif /* !__ASSEMBLY__ */
#endif /* !__ASM_ARCH_GICV3_H */

25
arch/arm64/Kconfig
View File

@ -123,6 +123,8 @@ config ARM64
select DMA_DIRECT_REMAP
select EDAC_SUPPORT
select FRAME_POINTER
select FUNCTION_ALIGNMENT_4B
select FUNCTION_ALIGNMENT_8B if DYNAMIC_FTRACE_WITH_CALL_OPS
select GENERIC_ALLOCATOR
select GENERIC_ARCH_TOPOLOGY
select GENERIC_CLOCKEVENTS_BROADCAST
@ -184,6 +186,8 @@ config ARM64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \
if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
@ -1470,10 +1474,23 @@ config XEN
help
Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
# include/linux/mmzone.h requires the following to be true:
#
# MAX_ORDER - 1 + PAGE_SHIFT <= SECTION_SIZE_BITS
#
# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS + 1 - PAGE_SHIFT:
#
# | SECTION_SIZE_BITS | PAGE_SHIFT | max MAX_ORDER | default MAX_ORDER |
# ----+-------------------+--------------+-----------------+--------------------+
# 4K | 27 | 12 | 16 | 11 |
# 16K | 27 | 14 | 14 | 12 |
# 64K | 29 | 16 | 14 | 14 |
config ARCH_FORCE_MAX_ORDER
int
int "Maximum zone order" if ARM64_4K_PAGES || ARM64_16K_PAGES
default "14" if ARM64_64K_PAGES
range 12 14 if ARM64_16K_PAGES
default "12" if ARM64_16K_PAGES
range 11 16 if ARM64_4K_PAGES
default "11"
help
The kernel memory allocator divides physically contiguous memory
@ -1486,7 +1503,7 @@ config ARCH_FORCE_MAX_ORDER
This config option is actually maximum order plus one. For example,
a value of 11 means that the largest free memory block is 2^10 pages.
We make sure that we can allocate upto a HugePage size for each configuration.
We make sure that we can allocate up to a HugePage size for each configuration.
Hence we have :
MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2
@ -1832,7 +1849,7 @@ config ARM64_PTR_AUTH_KERNEL
bool "Use pointer authentication for kernel"
default y
depends on ARM64_PTR_AUTH
depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_ARMV8_3
# Modern compilers insert a .note.gnu.property section note for PAC
# which is only understood by binutils starting with version 2.33.1.
depends on LD_IS_LLD || LD_VERSION >= 23301 || (CC_IS_GCC && GCC_VERSION < 90100)
@ -1857,7 +1874,7 @@ config CC_HAS_SIGN_RETURN_ADDRESS
# GCC 7, 8
def_bool $(cc-option,-msign-return-address=all)
config AS_HAS_PAC
config AS_HAS_ARMV8_3
def_bool $(cc-option,-Wa$(comma)-march=armv8.3-a)
config AS_HAS_CFI_NEGATE_RA_STATE

2
arch/arm64/Kconfig.platforms
View File

@ -187,7 +187,7 @@ config ARCH_MVEBU
select PINCTRL_ARMADA_CP110
select PINCTRL_AC5
help
This enables support for Marvell EBU familly, including:
This enables support for Marvell EBU family, including:
- Armada 3700 SoC Family
- Armada 7K SoC Family
- Armada 8K SoC Family

70
arch/arm64/Makefile
View File

@ -63,50 +63,37 @@ stack_protector_prepare: prepare0
include/generated/asm-offsets.h))
endif
ifeq ($(CONFIG_AS_HAS_ARMV8_2), y)
# make sure to pass the newest target architecture to -march.
asm-arch := armv8.2-a
endif
# Ensure that if the compiler supports branch protection we default it
# off, this will be overridden if we are using branch protection.
branch-prot-flags-y += $(call cc-option,-mbranch-protection=none)
ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
# We enable additional protection for leaf functions as there is some
# narrow potential for ROP protection benefits and no substantial
# performance impact has been observed.
PACRET-y := pac-ret+leaf
# Using a shadow call stack in leaf functions is too costly, so avoid PAC there
# as well when we may be patching PAC into SCS
PACRET-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) := pac-ret
ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=$(PACRET-y)+bti
KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti
else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y)
KBUILD_CFLAGS += -mbranch-protection=pac-ret
else
KBUILD_CFLAGS += -msign-return-address=non-leaf
endif
else
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=$(PACRET-y)
endif
# -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
# compiler to generate them and consequently to break the single image contract
# we pass it only to the assembler. This option is utilized only in case of non
# integrated assemblers.
ifeq ($(CONFIG_AS_HAS_PAC), y)
asm-arch := armv8.3-a
endif
endif
KBUILD_CFLAGS += $(branch-prot-flags-y)
ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
# make sure to pass the newest target architecture to -march.
asm-arch := armv8.4-a
KBUILD_CFLAGS += $(call cc-option,-mbranch-protection=none)
endif
# Tell the assembler to support instructions from the latest target
# architecture.
#
# For non-integrated assemblers we'll pass this on the command line, and for
# integrated assemblers we'll define ARM64_ASM_ARCH and ARM64_ASM_PREAMBLE for
# inline usage.
#
# We cannot pass the same arch flag to the compiler as this would allow it to
# freely generate instructions which are not supported by earlier architecture
# versions, which would prevent a single kernel image from working on earlier
# hardware.
ifeq ($(CONFIG_AS_HAS_ARMV8_5), y)
# make sure to pass the newest target architecture to -march.
asm-arch := armv8.5-a
asm-arch := armv8.5-a
else ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
asm-arch := armv8.4-a
else ifeq ($(CONFIG_AS_HAS_ARMV8_3), y)
asm-arch := armv8.3-a
else ifeq ($(CONFIG_AS_HAS_ARMV8_2), y)
asm-arch := armv8.2-a
endif
ifdef asm-arch
@ -139,7 +126,10 @@ endif
CHECKFLAGS += -D__aarch64__
ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y)
ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS),y)
KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2
else ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y)
KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
CC_FLAGS_FTRACE := -fpatchable-function-entry=2
endif

5
arch/arm64/include/asm/arch_gicv3.h
View File

@ -190,5 +190,10 @@ static inline void gic_arch_enable_irqs(void)
asm volatile ("msr daifclr, #3" : : : "memory");
}
static inline bool gic_has_relaxed_pmr_sync(void)
{
return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC);
}
#endif /* __ASSEMBLY__ */
#endif /* __ASM_ARCH_GICV3_H */

11
arch/arm64/include/asm/barrier.h
View File

@ -11,6 +11,8 @@
#include <linux/kasan-checks.h>
#include <asm/alternative-macros.h>
#define __nops(n) ".rept " #n "\nnop\n.endr\n"
#define nops(n) asm volatile(__nops(n))
@ -41,10 +43,11 @@
#ifdef CONFIG_ARM64_PSEUDO_NMI
#define pmr_sync() \
do { \
extern struct static_key_false gic_pmr_sync; \
\
if (static_branch_unlikely(&gic_pmr_sync)) \
dsb(sy); \
asm volatile( \
ALTERNATIVE_CB("dsb sy", \
ARM64_HAS_GIC_PRIO_RELAXED_SYNC, \
alt_cb_patch_nops) \
); \
} while(0)
#else
#define pmr_sync() do {} while (0)

14
arch/arm64/include/asm/cpufeature.h
View File

@ -769,6 +769,12 @@ static __always_inline bool system_supports_sme(void)
cpus_have_const_cap(ARM64_SME);
}
static __always_inline bool system_supports_sme2(void)
{
return IS_ENABLED(CONFIG_ARM64_SME) &&
cpus_have_const_cap(ARM64_SME2);
}
static __always_inline bool system_supports_fa64(void)
{
return IS_ENABLED(CONFIG_ARM64_SME) &&
@ -806,7 +812,7 @@ static inline bool system_has_full_ptr_auth(void)
static __always_inline bool system_uses_irq_prio_masking(void)
{
return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
cpus_have_const_cap(ARM64_HAS_GIC_PRIO_MASKING);
}
static inline bool system_supports_mte(void)
@ -864,7 +870,11 @@ static inline bool cpu_has_hw_af(void)
if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM))
return false;
mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
/*
* Use cached version to avoid emulated msr operation on KVM
* guests.
*/
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
return cpuid_feature_extract_unsigned_field(mmfr1,
ID_AA64MMFR1_EL1_HAFDBS_SHIFT);
}

2
arch/arm64/include/asm/efi.h
View File

@ -114,6 +114,8 @@ static inline unsigned long efi_get_kimg_min_align(void)
#define EFI_ALLOC_ALIGN SZ_64K
#define EFI_ALLOC_LIMIT ((1UL << 48) - 1)
extern unsigned long primary_entry_offset(void);
/*
* On ARM systems, virtually remapped UEFI runtime services are set up in two
* distinct stages:

8
arch/arm64/include/asm/el2_setup.h
View File

@ -53,10 +53,10 @@
cbz x0, .Lskip_spe_\@ // Skip if SPE not present
mrs_s x0, SYS_PMBIDR_EL1 // If SPE available at EL2,
and x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
and x0, x0, #(1 << PMBIDR_EL1_P_SHIFT)
cbnz x0, .Lskip_spe_el2_\@ // then permit sampling of physical
mov x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
1 << SYS_PMSCR_EL2_PA_SHIFT)
mov x0, #(1 << PMSCR_EL2_PCT_SHIFT | \
1 << PMSCR_EL2_PA_SHIFT)
msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter
.Lskip_spe_el2_\@:
mov x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
@ -177,7 +177,7 @@
/**
* Initialize EL2 registers to sane values. This should be called early on all
* cores that were booted in EL2. Note that everything gets initialised as
* if VHE was not evailable. The kernel context will be upgraded to VHE
* if VHE was not available. The kernel context will be upgraded to VHE
* if possible later on in the boot process
*
* Regs: x0, x1 and x2 are clobbered.

1
arch/arm64/include/asm/esr.h
View File

@ -350,6 +350,7 @@
#define ESR_ELx_SME_ISS_ILL 1
#define ESR_ELx_SME_ISS_SM_DISABLED 2
#define ESR_ELx_SME_ISS_ZA_DISABLED 3
#define ESR_ELx_SME_ISS_ZT_DISABLED 4
#ifndef __ASSEMBLY__
#include <asm/types.h>

30
arch/arm64/include/asm/fpsimd.h
View File

@ -61,7 +61,7 @@ extern void fpsimd_kvm_prepare(void);
struct cpu_fp_state {
struct user_fpsimd_state *st;
void *sve_state;
void *za_state;
void *sme_state;
u64 *svcr;
unsigned int sve_vl;
unsigned int sme_vl;
@ -105,6 +105,13 @@ static inline void *sve_pffr(struct thread_struct *thread)
return (char *)thread->sve_state + sve_ffr_offset(vl);
}
static inline void *thread_zt_state(struct thread_struct *thread)
{
/* The ZT register state is stored immediately after the ZA state */
unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread));
return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq);
}
extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
extern void sve_load_state(void const *state, u32 const *pfpsr,
int restore_ffr);
@ -112,12 +119,13 @@ extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
extern unsigned int sve_get_vl(void);
extern void sve_set_vq(unsigned long vq_minus_1);
extern void sme_set_vq(unsigned long vq_minus_1);
extern void za_save_state(void *state);
extern void za_load_state(void const *state);
extern void sme_save_state(void *state, int zt);
extern void sme_load_state(void const *state, int zt);
struct arm64_cpu_capabilities;
extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern u64 read_zcr_features(void);
@ -355,14 +363,20 @@ extern int sme_get_current_vl(void);
/*
* Return how many bytes of memory are required to store the full SME
* specific state (currently just ZA) for task, given task's currently
* configured vector length.
* specific state for task, given task's currently configured vector
* length.
*/
static inline size_t za_state_size(struct task_struct const *task)
static inline size_t sme_state_size(struct task_struct const *task)
{
unsigned int vl = task_get_sme_vl(task);
size_t size;
return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
if (system_supports_sme2())
size += ZT_SIG_REG_SIZE;
return size;
}
#else
@ -382,7 +396,7 @@ static inline int sme_max_virtualisable_vl(void) { return 0; }
static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
static inline int sme_get_current_vl(void) { return -EINVAL; }
static inline size_t za_state_size(struct task_struct const *task)
static inline size_t sme_state_size(struct task_struct const *task)
{
return 0;
}

22
arch/arm64/include/asm/fpsimdmacros.h
View File

@ -220,6 +220,28 @@
| ((\offset) & 7)
.endm
/*
* LDR (ZT0)
*
* LDR ZT0, nx
*/
.macro _ldr_zt nx
_check_general_reg \nx
.inst 0xe11f8000 \
| (\nx << 5)
.endm
/*
* STR (ZT0)
*
* STR ZT0, nx
*/
.macro _str_zt nx
_check_general_reg \nx
.inst 0xe13f8000 \
| (\nx << 5)
.endm
/*
* Zero the entire ZA array
* ZERO ZA

15
arch/arm64/include/asm/ftrace.h
View File

@ -62,20 +62,7 @@ extern unsigned long ftrace_graph_call;
extern void return_to_handler(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
/*
* Adjust addr to point at the BL in the callsite.
* See ftrace_init_nop() for the callsite sequence.
*/
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
return addr + AARCH64_INSN_SIZE;
/*
* addr is the address of the mcount call instruction.
* recordmcount does the necessary offset calculation.
*/
return addr;
}
unsigned long ftrace_call_adjust(unsigned long addr);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
struct dyn_ftrace;

14
arch/arm64/include/asm/hwcap.h
View File

@ -31,12 +31,20 @@
#define COMPAT_HWCAP_VFPD32 (1 << 19)
#define COMPAT_HWCAP_LPAE (1 << 20)
#define COMPAT_HWCAP_EVTSTRM (1 << 21)
#define COMPAT_HWCAP_FPHP (1 << 22)
#define COMPAT_HWCAP_ASIMDHP (1 << 23)
#define COMPAT_HWCAP_ASIMDDP (1 << 24)
#define COMPAT_HWCAP_ASIMDFHM (1 << 25)
#define COMPAT_HWCAP_ASIMDBF16 (1 << 26)
#define COMPAT_HWCAP_I8MM (1 << 27)
#define COMPAT_HWCAP2_AES (1 << 0)
#define COMPAT_HWCAP2_PMULL (1 << 1)
#define COMPAT_HWCAP2_SHA1 (1 << 2)
#define COMPAT_HWCAP2_SHA2 (1 << 3)
#define COMPAT_HWCAP2_CRC32 (1 << 4)
#define COMPAT_HWCAP2_SB (1 << 5)
#define COMPAT_HWCAP2_SSBS (1 << 6)
#ifndef __ASSEMBLY__
#include <linux/log2.h>
@ -123,6 +131,12 @@
#define KERNEL_HWCAP_CSSC __khwcap2_feature(CSSC)
#define KERNEL_HWCAP_RPRFM __khwcap2_feature(RPRFM)
#define KERNEL_HWCAP_SVE2P1 __khwcap2_feature(SVE2P1)
#define KERNEL_HWCAP_SME2 __khwcap2_feature(SME2)
#define KERNEL_HWCAP_SME2P1 __khwcap2_feature(SME2P1)
#define KERNEL_HWCAP_SME_I16I32 __khwcap2_feature(SME_I16I32)
#define KERNEL_HWCAP_SME_BI32I32 __khwcap2_feature(SME_BI32I32)
#define KERNEL_HWCAP_SME_B16B16 __khwcap2_feature(SME_B16B16)
#define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16)
/*
* This yields a mask that user programs can use to figure out what

1
arch/arm64/include/asm/insn.h
View File

@ -420,6 +420,7 @@ __AARCH64_INSN_FUNCS(sb, 0xFFFFFFFF, 0xD50330FF)
__AARCH64_INSN_FUNCS(clrex, 0xFFFFF0FF, 0xD503305F)
__AARCH64_INSN_FUNCS(ssbb, 0xFFFFFFFF, 0xD503309F)
__AARCH64_INSN_FUNCS(pssbb, 0xFFFFFFFF, 0xD503349F)
__AARCH64_INSN_FUNCS(bti, 0xFFFFFF3F, 0xD503241f)
#undef __AARCH64_INSN_FUNCS

209
arch/arm64/include/asm/irqflags.h
View File

@ -21,43 +21,77 @@
* exceptions should be unmasked.
*/
/*
* CPU interrupt mask handling.
*/
static inline void arch_local_irq_enable(void)
static __always_inline bool __irqflags_uses_pmr(void)
{
if (system_has_prio_mask_debugging()) {
u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
alternative_has_feature_unlikely(ARM64_HAS_GIC_PRIO_MASKING);
}
static __always_inline void __daif_local_irq_enable(void)
{
barrier();
asm volatile("msr daifclr, #3");
barrier();
}
static __always_inline void __pmr_local_irq_enable(void)
{
if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) {
u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
}
asm volatile(ALTERNATIVE(
"msr daifclr, #3 // arch_local_irq_enable",
__msr_s(SYS_ICC_PMR_EL1, "%0"),
ARM64_HAS_IRQ_PRIO_MASKING)
:
: "r" ((unsigned long) GIC_PRIO_IRQON)
: "memory");
barrier();
write_sysreg_s(GIC_PRIO_IRQON, SYS_ICC_PMR_EL1);
pmr_sync();
barrier();
}
static inline void arch_local_irq_enable(void)
{
if (__irqflags_uses_pmr()) {
__pmr_local_irq_enable();
} else {
__daif_local_irq_enable();
}
}
static __always_inline void __daif_local_irq_disable(void)
{
barrier();
asm volatile("msr daifset, #3");
barrier();
}
static __always_inline void __pmr_local_irq_disable(void)
{
if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) {
u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
}
barrier();
write_sysreg_s(GIC_PRIO_IRQOFF, SYS_ICC_PMR_EL1);
barrier();
}
static inline void arch_local_irq_disable(void)
{
if (system_has_prio_mask_debugging()) {
u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
if (__irqflags_uses_pmr()) {
__pmr_local_irq_disable();
} else {
__daif_local_irq_disable();
}
}
asm volatile(ALTERNATIVE(
"msr daifset, #3 // arch_local_irq_disable",
__msr_s(SYS_ICC_PMR_EL1, "%0"),
ARM64_HAS_IRQ_PRIO_MASKING)
:
: "r" ((unsigned long) GIC_PRIO_IRQOFF)
: "memory");
static __always_inline unsigned long __daif_local_save_flags(void)
{
return read_sysreg(daif);
}
static __always_inline unsigned long __pmr_local_save_flags(void)
{
return read_sysreg_s(SYS_ICC_PMR_EL1);
}
/*
@ -65,69 +99,108 @@ static inline void arch_local_irq_disable(void)
*/
static inline unsigned long arch_local_save_flags(void)
{
unsigned long flags;
if (__irqflags_uses_pmr()) {
return __pmr_local_save_flags();
} else {
return __daif_local_save_flags();
}
}
asm volatile(ALTERNATIVE(
"mrs %0, daif",
__mrs_s("%0", SYS_ICC_PMR_EL1),
ARM64_HAS_IRQ_PRIO_MASKING)
: "=&r" (flags)
:
: "memory");
static __always_inline bool __daif_irqs_disabled_flags(unsigned long flags)
{
return flags & PSR_I_BIT;
}
static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags)
{
return flags != GIC_PRIO_IRQON;
}
static inline bool arch_irqs_disabled_flags(unsigned long flags)
{
if (__irqflags_uses_pmr()) {
return __pmr_irqs_disabled_flags(flags);
} else {
return __daif_irqs_disabled_flags(flags);
}
}
static __always_inline bool __daif_irqs_disabled(void)
{
return __daif_irqs_disabled_flags(__daif_local_save_flags());
}
static __always_inline bool __pmr_irqs_disabled(void)
{
return __pmr_irqs_disabled_flags(__pmr_local_save_flags());
}
static inline bool arch_irqs_disabled(void)
{
if (__irqflags_uses_pmr()) {
return __pmr_irqs_disabled();
} else {
return __daif_irqs_disabled();
}
}
static __always_inline unsigned long __daif_local_irq_save(void)
{
unsigned long flags = __daif_local_save_flags();
__daif_local_irq_disable();
return flags;
}
static inline int arch_irqs_disabled_flags(unsigned long flags)
static __always_inline unsigned long __pmr_local_irq_save(void)
{
int res;
asm volatile(ALTERNATIVE(
"and %w0, %w1, #" __stringify(PSR_I_BIT),
"eor %w0, %w1, #" __stringify(GIC_PRIO_IRQON),
ARM64_HAS_IRQ_PRIO_MASKING)
: "=&r" (res)
: "r" ((int) flags)
: "memory");
return res;
}
static inline int arch_irqs_disabled(void)
{
return arch_irqs_disabled_flags(arch_local_save_flags());
}
static inline unsigned long arch_local_irq_save(void)
{
unsigned long flags;
flags = arch_local_save_flags();
unsigned long flags = __pmr_local_save_flags();
/*
* There are too many states with IRQs disabled, just keep the current
* state if interrupts are already disabled/masked.
*/
if (!arch_irqs_disabled_flags(flags))
arch_local_irq_disable();
if (!__pmr_irqs_disabled_flags(flags))
__pmr_local_irq_disable();
return flags;
}
static inline unsigned long arch_local_irq_save(void)
{
if (__irqflags_uses_pmr()) {
return __pmr_local_irq_save();
} else {
return __daif_local_irq_save();
}
}
static __always_inline void __daif_local_irq_restore(unsigned long flags)
{
barrier();
write_sysreg(flags, daif);
barrier();
}
static __always_inline void __pmr_local_irq_restore(unsigned long flags)
{
barrier();
write_sysreg_s(flags, SYS_ICC_PMR_EL1);
pmr_sync();
barrier();
}
/*
* restore saved IRQ state
*/
static inline void arch_local_irq_restore(unsigned long flags)
{
asm volatile(ALTERNATIVE(
"msr daif, %0",
__msr_s(SYS_ICC_PMR_EL1, "%0"),
ARM64_HAS_IRQ_PRIO_MASKING)
:
: "r" (flags)
: "memory");
pmr_sync();
if (__irqflags_uses_pmr()) {
__pmr_local_irq_restore(flags);
} else {
__daif_local_irq_restore(flags);
}
}
#endif /* __ASM_IRQFLAGS_H */

4
arch/arm64/include/asm/linkage.h
View File

@ -5,8 +5,8 @@
#include <asm/assembler.h>
#endif
#define __ALIGN .align 2
#define __ALIGN_STR ".align 2"
#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT
#define __ALIGN_STR ".balign " #CONFIG_FUNCTION_ALIGNMENT
/*
* When using in-kernel BTI we need to ensure that PCS-conformant

2
arch/arm64/include/asm/patching.h
View File

@ -7,6 +7,8 @@
int aarch64_insn_read(void *addr, u32 *insnp);
int aarch64_insn_write(void *addr, u32 insn);
int aarch64_insn_write_literal_u64(void *addr, u64 val);
int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);

8
arch/arm64/include/asm/pgtable.h
View File

@ -275,6 +275,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
}
extern void __sync_icache_dcache(pte_t pteval);
bool pgattr_change_is_safe(u64 old, u64 new);
/*
* PTE bits configuration in the presence of hardware Dirty Bit Management
@ -292,7 +293,7 @@ extern void __sync_icache_dcache(pte_t pteval);
* PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
*/
static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep,
pte_t pte)
{
pte_t old_pte;
@ -318,6 +319,9 @@ static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
"%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
__func__, pte_val(old_pte), pte_val(pte));
VM_WARN_ONCE(!pgattr_change_is_safe(pte_val(old_pte), pte_val(pte)),
"%s: unsafe attribute change: 0x%016llx -> 0x%016llx",
__func__, pte_val(old_pte), pte_val(pte));
}
static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
@ -346,7 +350,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
mte_sync_tags(old_pte, pte);
}
__check_racy_pte_update(mm, ptep, pte);
__check_safe_pte_update(mm, ptep, pte);
set_pte(ptep, pte);
}

2
arch/arm64/include/asm/processor.h
View File

@ -161,7 +161,7 @@ struct thread_struct {
enum fp_type fp_type; /* registers FPSIMD or SVE? */
unsigned int fpsimd_cpu;
void *sve_state; /* SVE registers, if any */
void *za_state; /* ZA register, if any */
void *sme_state; /* ZA and ZT state, if any */
unsigned int vl[ARM64_VEC_MAX]; /* vector length */
unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
unsigned long fault_address; /* fault info */

2
arch/arm64/include/asm/ptrace.h
View File

@ -194,7 +194,7 @@ struct pt_regs {
u32 unused2;
#endif
u64 sdei_ttbr1;
/* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */
/* Only valid when ARM64_HAS_GIC_PRIO_MASKING is enabled. */
u64 pmr_save;
u64 stackframe[2];

7
arch/arm64/include/asm/scs.h
View File

@ -10,15 +10,16 @@
#ifdef CONFIG_SHADOW_CALL_STACK
scs_sp .req x18
.macro scs_load tsk
ldr scs_sp, [\tsk, #TSK_TI_SCS_SP]
.macro scs_load_current
get_current_task scs_sp
ldr scs_sp, [scs_sp, #TSK_TI_SCS_SP]
.endm
.macro scs_save tsk
str scs_sp, [\tsk, #TSK_TI_SCS_SP]
.endm
#else
.macro scs_load tsk
.macro scs_load_current
.endm
.macro scs_save tsk

106
arch/arm64/include/asm/sysreg.h
View File

@ -216,101 +216,22 @@
#define SYS_PAR_EL1_FST GENMASK(6, 1)
/*** Statistical Profiling Extension ***/
/* ID registers */
#define SYS_PMSIDR_EL1 sys_reg(3, 0, 9, 9, 7)
#define SYS_PMSIDR_EL1_FE_SHIFT 0
#define SYS_PMSIDR_EL1_FT_SHIFT 1
#define SYS_PMSIDR_EL1_FL_SHIFT 2
#define SYS_PMSIDR_EL1_ARCHINST_SHIFT 3
#define SYS_PMSIDR_EL1_LDS_SHIFT 4
#define SYS_PMSIDR_EL1_ERND_SHIFT 5
#define SYS_PMSIDR_EL1_INTERVAL_SHIFT 8
#define SYS_PMSIDR_EL1_INTERVAL_MASK 0xfUL
#define SYS_PMSIDR_EL1_MAXSIZE_SHIFT 12
#define SYS_PMSIDR_EL1_MAXSIZE_MASK 0xfUL
#define SYS_PMSIDR_EL1_COUNTSIZE_SHIFT 16
#define SYS_PMSIDR_EL1_COUNTSIZE_MASK 0xfUL
#define SYS_PMBIDR_EL1 sys_reg(3, 0, 9, 10, 7)
#define SYS_PMBIDR_EL1_ALIGN_SHIFT 0
#define SYS_PMBIDR_EL1_ALIGN_MASK 0xfU
#define SYS_PMBIDR_EL1_P_SHIFT 4
#define SYS_PMBIDR_EL1_F_SHIFT 5
/* Sampling controls */
#define SYS_PMSCR_EL1 sys_reg(3, 0, 9, 9, 0)
#define SYS_PMSCR_EL1_E0SPE_SHIFT 0
#define SYS_PMSCR_EL1_E1SPE_SHIFT 1
#define SYS_PMSCR_EL1_CX_SHIFT 3
#define SYS_PMSCR_EL1_PA_SHIFT 4
#define SYS_PMSCR_EL1_TS_SHIFT 5
#define SYS_PMSCR_EL1_PCT_SHIFT 6
#define SYS_PMSCR_EL2 sys_reg(3, 4, 9, 9, 0)
#define SYS_PMSCR_EL2_E0HSPE_SHIFT 0
#define SYS_PMSCR_EL2_E2SPE_SHIFT 1
#define SYS_PMSCR_EL2_CX_SHIFT 3
#define SYS_PMSCR_EL2_PA_SHIFT 4
#define SYS_PMSCR_EL2_TS_SHIFT 5
#define SYS_PMSCR_EL2_PCT_SHIFT 6
#define SYS_PMSICR_EL1 sys_reg(3, 0, 9, 9, 2)
#define SYS_PMSIRR_EL1 sys_reg(3, 0, 9, 9, 3)
#define SYS_PMSIRR_EL1_RND_SHIFT 0
#define SYS_PMSIRR_EL1_INTERVAL_SHIFT 8
#define SYS_PMSIRR_EL1_INTERVAL_MASK 0xffffffUL
/* Filtering controls */
#define SYS_PMSNEVFR_EL1 sys_reg(3, 0, 9, 9, 1)
#define SYS_PMSFCR_EL1 sys_reg(3, 0, 9, 9, 4)
#define SYS_PMSFCR_EL1_FE_SHIFT 0
#define SYS_PMSFCR_EL1_FT_SHIFT 1
#define SYS_PMSFCR_EL1_FL_SHIFT 2
#define SYS_PMSFCR_EL1_B_SHIFT 16
#define SYS_PMSFCR_EL1_LD_SHIFT 17
#define SYS_PMSFCR_EL1_ST_SHIFT 18
#define SYS_PMSEVFR_EL1 sys_reg(3, 0, 9, 9, 5)
#define SYS_PMSEVFR_EL1_RES0_8_2 \
#define PMSEVFR_EL1_RES0_IMP \
(GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\
BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0))
#define SYS_PMSEVFR_EL1_RES0_8_3 \
(SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11)))
#define SYS_PMSLATFR_EL1 sys_reg(3, 0, 9, 9, 6)
#define SYS_PMSLATFR_EL1_MINLAT_SHIFT 0
/* Buffer controls */
#define SYS_PMBLIMITR_EL1 sys_reg(3, 0, 9, 10, 0)
#define SYS_PMBLIMITR_EL1_E_SHIFT 0
#define SYS_PMBLIMITR_EL1_FM_SHIFT 1
#define SYS_PMBLIMITR_EL1_FM_MASK 0x3UL
#define SYS_PMBLIMITR_EL1_FM_STOP_IRQ (0 << SYS_PMBLIMITR_EL1_FM_SHIFT)
#define SYS_PMBPTR_EL1 sys_reg(3, 0, 9, 10, 1)
#define PMSEVFR_EL1_RES0_V1P1 \
(PMSEVFR_EL1_RES0_IMP & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11)))
#define PMSEVFR_EL1_RES0_V1P2 \
(PMSEVFR_EL1_RES0_V1P1 & ~BIT_ULL(6))
/* Buffer error reporting */
#define SYS_PMBSR_EL1 sys_reg(3, 0, 9, 10, 3)
#define SYS_PMBSR_EL1_COLL_SHIFT 16
#define SYS_PMBSR_EL1_S_SHIFT 17
#define SYS_PMBSR_EL1_EA_SHIFT 18
#define SYS_PMBSR_EL1_DL_SHIFT 19
#define SYS_PMBSR_EL1_EC_SHIFT 26
#define SYS_PMBSR_EL1_EC_MASK 0x3fUL
#define PMBSR_EL1_FAULT_FSC_SHIFT PMBSR_EL1_MSS_SHIFT
#define PMBSR_EL1_FAULT_FSC_MASK PMBSR_EL1_MSS_MASK
#define SYS_PMBSR_EL1_EC_BUF (0x0UL << SYS_PMBSR_EL1_EC_SHIFT)
#define SYS_PMBSR_EL1_EC_FAULT_S1 (0x24UL << SYS_PMBSR_EL1_EC_SHIFT)
#define SYS_PMBSR_EL1_EC_FAULT_S2 (0x25UL << SYS_PMBSR_EL1_EC_SHIFT)
#define PMBSR_EL1_BUF_BSC_SHIFT PMBSR_EL1_MSS_SHIFT
#define PMBSR_EL1_BUF_BSC_MASK PMBSR_EL1_MSS_MASK
#define SYS_PMBSR_EL1_FAULT_FSC_SHIFT 0
#define SYS_PMBSR_EL1_FAULT_FSC_MASK 0x3fUL
#define SYS_PMBSR_EL1_BUF_BSC_SHIFT 0
#define SYS_PMBSR_EL1_BUF_BSC_MASK 0x3fUL
#define SYS_PMBSR_EL1_BUF_BSC_FULL (0x1UL << SYS_PMBSR_EL1_BUF_BSC_SHIFT)
#define PMBSR_EL1_BUF_BSC_FULL 0x1UL
/*** End of Statistical Profiling Extension ***/
@ -575,6 +496,7 @@
#define SCTLR_ELx_DSSBS (BIT(44))
#define SCTLR_ELx_ATA (BIT(43))
#define SCTLR_ELx_EE_SHIFT 25
#define SCTLR_ELx_ENIA_SHIFT 31
#define SCTLR_ELx_ITFSB (BIT(37))
@ -583,7 +505,7 @@
#define SCTLR_ELx_LSMAOE (BIT(29))
#define SCTLR_ELx_nTLSMD (BIT(28))
#define SCTLR_ELx_ENDA (BIT(27))
#define SCTLR_ELx_EE (BIT(25))
#define SCTLR_ELx_EE (BIT(SCTLR_ELx_EE_SHIFT))
#define SCTLR_ELx_EIS (BIT(22))
#define SCTLR_ELx_IESB (BIT(21))
#define SCTLR_ELx_TSCXT (BIT(20))
@ -809,8 +731,8 @@
#define ARM64_FEATURE_FIELD_BITS 4
/* Create a mask for the feature bits of the specified feature. */
#define ARM64_FEATURE_MASK(x) (GENMASK_ULL(x##_SHIFT + ARM64_FEATURE_FIELD_BITS - 1, x##_SHIFT))
/* Defined for compatibility only, do not add new users. */
#define ARM64_FEATURE_MASK(x) (x##_MASK)
#ifdef __ASSEMBLY__

6
arch/arm64/include/uapi/asm/hwcap.h
View File

@ -96,5 +96,11 @@
#define HWCAP2_CSSC (1UL << 34)
#define HWCAP2_RPRFM (1UL << 35)
#define HWCAP2_SVE2P1 (1UL << 36)
#define HWCAP2_SME2 (1UL << 37)
#define HWCAP2_SME2P1 (1UL << 38)
#define HWCAP2_SME_I16I32 (1UL << 39)
#define HWCAP2_SME_BI32I32 (1UL << 40)
#define HWCAP2_SME_B16B16 (1UL << 41)
#define HWCAP2_SME_F16F16 (1UL << 42)
#endif /* _UAPI__ASM_HWCAP_H */

27
arch/arm64/include/uapi/asm/sigcontext.h
View File

@ -144,6 +144,14 @@ struct sve_context {
#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */
/* TPIDR2_EL0 context */
#define TPIDR2_MAGIC 0x54504902
struct tpidr2_context {
struct _aarch64_ctx head;
__u64 tpidr2;
};
#define ZA_MAGIC 0x54366345
struct za_context {
@ -152,6 +160,14 @@ struct za_context {
__u16 __reserved[3];
};
#define ZT_MAGIC 0x5a544e01
struct zt_context {
struct _aarch64_ctx head;
__u16 nregs;
__u16 __reserved[3];
};
#endif /* !__ASSEMBLY__ */
#include <asm/sve_context.h>
@ -304,4 +320,15 @@ struct za_context {
#define ZA_SIG_CONTEXT_SIZE(vq) \
(ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
#define ZT_SIG_REG_SIZE 512
#define ZT_SIG_REG_BYTES (ZT_SIG_REG_SIZE / 8)
#define ZT_SIG_REGS_OFFSET sizeof(struct zt_context)
#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n)
#define ZT_SIG_CONTEXT_SIZE(n) \
(sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n))
#endif /* _UAPI__ASM_SIGCONTEXT_H */

4
arch/arm64/kernel/asm-offsets.c
View File

@ -9,6 +9,7 @@
#include <linux/arm_sdei.h>
#include <linux/sched.h>
#include <linux/ftrace.h>
#include <linux/kexec.h>
#include <linux/mm.h>
#include <linux/dma-mapping.h>
@ -193,6 +194,9 @@ int main(void)
DEFINE(KIMAGE_HEAD, offsetof(struct kimage, head));
DEFINE(KIMAGE_START, offsetof(struct kimage, start));
BLANK();
#endif
#ifdef CONFIG_FUNCTION_TRACER
DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func));
#endif
return 0;
}

293
arch/arm64/kernel/cpufeature.c
View File

@ -65,6 +65,7 @@
#include <linux/bsearch.h>
#include <linux/cpumask.h>
#include <linux/crash_dump.h>
#include <linux/kstrtox.h>
#include <linux/sort.h>
#include <linux/stop_machine.h>
#include <linux/sysfs.h>
@ -282,16 +283,26 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I32_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0),
ARM64_FTR_END,
@ -444,8 +455,8 @@ static const struct arm64_ftr_bits ftr_mvfr0[] = {
static const struct arm64_ftr_bits ftr_mvfr1[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDFMAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDSP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDInt_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDLS_SHIFT, 4, 0),
@ -529,12 +540,12 @@ static const struct arm64_ftr_bits ftr_id_mmfr5[] = {
};
static const struct arm64_ftr_bits ftr_id_isar6[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SPECRES_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_JSCVT_SHIFT, 4, 0),
ARM64_FTR_END,
};
@ -562,7 +573,7 @@ static const struct arm64_ftr_bits ftr_id_pfr1[] = {
};
static const struct arm64_ftr_bits ftr_id_pfr2[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_CSV3_SHIFT, 4, 0),
ARM64_FTR_END,
};
@ -1795,7 +1806,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
static int __init parse_kpti(char *str)
{
bool enabled;
int ret = strtobool(str, &enabled);
int ret = kstrtobool(str, &enabled);
if (ret)
return ret;
@ -2039,14 +2050,50 @@ static bool enable_pseudo_nmi;
static int __init early_enable_pseudo_nmi(char *p)
{
return strtobool(p, &enable_pseudo_nmi);
return kstrtobool(p, &enable_pseudo_nmi);
}
early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi);
static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
int scope)
{
return enable_pseudo_nmi && has_useable_gicv3_cpuif(entry, scope);
/*
* ARM64_HAS_GIC_CPUIF_SYSREGS has a lower index, and is a boot CPU
* feature, so will be detected earlier.
*/
BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_MASKING <= ARM64_HAS_GIC_CPUIF_SYSREGS);
if (!cpus_have_cap(ARM64_HAS_GIC_CPUIF_SYSREGS))
return false;
return enable_pseudo_nmi;
}
static bool has_gic_prio_relaxed_sync(const struct arm64_cpu_capabilities *entry,
int scope)
{
/*
* If we're not using priority masking then we won't be poking PMR_EL1,
* and there's no need to relax synchronization of writes to it, and
* ICC_CTLR_EL1 might not be accessible and we must avoid reads from
* that.
*
* ARM64_HAS_GIC_PRIO_MASKING has a lower index, and is a boot CPU
* feature, so will be detected earlier.
*/
BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_RELAXED_SYNC <= ARM64_HAS_GIC_PRIO_MASKING);
if (!cpus_have_cap(ARM64_HAS_GIC_PRIO_MASKING))
return false;
/*
* When Priority Mask Hint Enable (PMHE) == 0b0, PMR is not used as a
* hint for interrupt distribution, a DSB is not necessary when
* unmasking IRQs via PMR, and we can relax the barrier to a NOP.
*
* Linux itself doesn't use 1:N distribution, so has no need to
* set PMHE. The only reason to have it set is if EL3 requires it
* (and we can't change it).
*/
return (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) == 0;
}
#endif
@ -2142,7 +2189,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
},
{
.desc = "GIC system register CPU interface",
.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
.capability = ARM64_HAS_GIC_CPUIF_SYSREGS,
.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
.matches = has_useable_gicv3_cpuif,
.sys_reg = SYS_ID_AA64PFR0_EL1,
@ -2534,14 +2581,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
* Depends on having GICv3
*/
.desc = "IRQ priority masking",
.capability = ARM64_HAS_IRQ_PRIO_MASKING,
.capability = ARM64_HAS_GIC_PRIO_MASKING,
.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
.matches = can_use_gic_priorities,
.sys_reg = SYS_ID_AA64PFR0_EL1,
.field_pos = ID_AA64PFR0_EL1_GIC_SHIFT,
.field_width = 4,
.sign = FTR_UNSIGNED,
.min_field_value = 1,
},
{
/*
* Depends on ARM64_HAS_GIC_PRIO_MASKING
*/
.capability = ARM64_HAS_GIC_PRIO_RELAXED_SYNC,
.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
.matches = has_gic_prio_relaxed_sync,
},
#endif
#ifdef CONFIG_ARM64_E0PD
@ -2649,6 +2699,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
.cpu_enable = fa64_kernel_enable,
},
{
.desc = "SME2",
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.capability = ARM64_SME2,
.sys_reg = SYS_ID_AA64PFR1_EL1,
.sign = FTR_UNSIGNED,
.field_pos = ID_AA64PFR1_EL1_SME_SHIFT,
.field_width = ID_AA64PFR1_EL1_SME_WIDTH,
.min_field_value = ID_AA64PFR1_EL1_SME_SME2,
.matches = has_cpuid_feature,
.cpu_enable = sme2_kernel_enable,
},
#endif /* CONFIG_ARM64_SME */
{
.desc = "WFx with timeout",
@ -2688,13 +2750,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
{},
};
#define HWCAP_CPUID_MATCH(reg, field, width, s, min_value) \
#define HWCAP_CPUID_MATCH(reg, field, min_value) \
.matches = has_user_cpuid_feature, \
.sys_reg = reg, \
.field_pos = field, \
.field_width = width, \
.sign = s, \
.min_field_value = min_value,
.sys_reg = SYS_##reg, \
.field_pos = reg##_##field##_SHIFT, \
.field_width = reg##_##field##_WIDTH, \
.sign = reg##_##field##_SIGNED, \
.min_field_value = reg##_##field##_##min_value,
#define __HWCAP_CAP(name, cap_type, cap) \
.desc = name, \
@ -2702,10 +2764,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.hwcap_type = cap_type, \
.hwcap = cap, \
#define HWCAP_CAP(reg, field, width, s, min_value, cap_type, cap) \
#define HWCAP_CAP(reg, field, min_value, cap_type, cap) \
{ \
__HWCAP_CAP(#cap, cap_type, cap) \
HWCAP_CPUID_MATCH(reg, field, width, s, min_value) \
HWCAP_CPUID_MATCH(reg, field, min_value) \
}
#define HWCAP_MULTI_CAP(list, cap_type, cap) \
@ -2724,115 +2786,114 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
#ifdef CONFIG_ARM64_PTR_AUTH
static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = {
{
HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_APA_SHIFT,
4, FTR_UNSIGNED,
ID_AA64ISAR1_EL1_APA_PAuth)
HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, APA, PAuth)
},
{
HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_APA3_SHIFT,
4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_APA3_PAuth)
HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, APA3, PAuth)
},
{
HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_API_SHIFT,
4, FTR_UNSIGNED, ID_AA64ISAR1_EL1_API_PAuth)
HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, API, PAuth)
},
{},
};
static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
{
HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_GPA_SHIFT,
4, FTR_UNSIGNED, ID_AA64ISAR1_EL1_GPA_IMP)
HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPA, IMP)
},
{
HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_GPA3_SHIFT,
4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_GPA3_IMP)
HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, GPA3, IMP)
},
{
HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_GPI_SHIFT,
4, FTR_UNSIGNED, ID_AA64ISAR1_EL1_GPI_IMP)
HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPI, IMP)
},
{},
};
#endif
static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_JSCVT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_FCMA_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_LRCPC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_LRCPC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_FRINTTS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_SB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_EBF16),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM),
HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
HWCAP_CAP(ID_AA64ISAR0_EL1, SHA1, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA1),
HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA256, CAP_HWCAP, KERNEL_HWCAP_SHA2),
HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA512, CAP_HWCAP, KERNEL_HWCAP_SHA512),
HWCAP_CAP(ID_AA64ISAR0_EL1, CRC32, IMP, CAP_HWCAP, KERNEL_HWCAP_CRC32),
HWCAP_CAP(ID_AA64ISAR0_EL1, ATOMIC, IMP, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
HWCAP_CAP(ID_AA64ISAR0_EL1, RDM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
HWCAP_CAP(ID_AA64ISAR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA3),
HWCAP_CAP(ID_AA64ISAR0_EL1, SM3, IMP, CAP_HWCAP, KERNEL_HWCAP_SM3),
HWCAP_CAP(ID_AA64ISAR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SM4),
HWCAP_CAP(ID_AA64ISAR0_EL1, DP, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
HWCAP_CAP(ID_AA64ISAR0_EL1, FHM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG),
HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP),
HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP),
HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, FP16, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
HWCAP_CAP(ID_AA64PFR0_EL1, DIT, IMP, CAP_HWCAP, KERNEL_HWCAP_DIT),
HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, IMP, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, DPB2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
HWCAP_CAP(ID_AA64ISAR1_EL1, JSCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
HWCAP_CAP(ID_AA64ISAR1_EL1, FCMA, IMP, CAP_HWCAP, KERNEL_HWCAP_FCMA),
HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, IMP, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, LRCPC2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
HWCAP_CAP(ID_AA64ISAR1_EL1, FRINTTS, IMP, CAP_HWCAP, KERNEL_HWCAP_FRINT),
HWCAP_CAP(ID_AA64ISAR1_EL1, SB, IMP, CAP_HWCAP, KERNEL_HWCAP_SB),
HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_BF16),
HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16),
HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH),
HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM),
HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT),
#ifdef CONFIG_ARM64_SVE
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BitPerm_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BF16_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BF16_EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SHA3_IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SM4_IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_I8MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_F32MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_F64MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16),
HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
#endif
HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SSBS_SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
HWCAP_CAP(ID_AA64PFR1_EL1, SSBS, SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
#ifdef CONFIG_ARM64_BTI
HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_BT_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_BT_IMP, CAP_HWCAP, KERNEL_HWCAP_BTI),
HWCAP_CAP(ID_AA64PFR1_EL1, BT, IMP, CAP_HWCAP, KERNEL_HWCAP_BTI),
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
#endif
#ifdef CONFIG_ARM64_MTE
HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_MTE_MTE2, CAP_HWCAP, KERNEL_HWCAP_MTE),
HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_MTE_MTE3, CAP_HWCAP, KERNEL_HWCAP_MTE3),
HWCAP_CAP(ID_AA64PFR1_EL1, MTE, MTE2, CAP_HWCAP, KERNEL_HWCAP_MTE),
HWCAP_CAP(ID_AA64PFR1_EL1, MTE, MTE3, CAP_HWCAP, KERNEL_HWCAP_MTE3),
#endif /* CONFIG_ARM64_MTE */
HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_CSSC_IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_RPRFM_IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV),
HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP),
HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES),
HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
#ifdef CONFIG_ARM64_SME
HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SME_IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_FA64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F64F64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I8I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F32F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
#endif /* CONFIG_ARM64_SME */
{},
};
@ -2862,15 +2923,23 @@ static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope)
static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
#ifdef CONFIG_COMPAT
HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON),
HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_EL1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
HWCAP_CAP(MVFR1_EL1, SIMDFMAC, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
/* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */
HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
HWCAP_CAP(MVFR0_EL1, FPDP, VFPv3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
HWCAP_CAP(MVFR0_EL1, FPDP, VFPv3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
HWCAP_CAP(MVFR1_EL1, FPHP, FP16, CAP_COMPAT_HWCAP, COMPAT_HWCAP_FPHP),
HWCAP_CAP(MVFR1_EL1, SIMDHP, SIMDHP_FLOAT, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDHP),
HWCAP_CAP(ID_ISAR5_EL1, AES, VMULL, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
HWCAP_CAP(ID_ISAR5_EL1, AES, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
HWCAP_CAP(ID_ISAR5_EL1, SHA1, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
HWCAP_CAP(ID_ISAR5_EL1, SHA2, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
HWCAP_CAP(ID_ISAR5_EL1, CRC32, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
HWCAP_CAP(ID_ISAR6_EL1, DP, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDDP),
HWCAP_CAP(ID_ISAR6_EL1, FHM, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDFHM),
HWCAP_CAP(ID_ISAR6_EL1, SB, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SB),
HWCAP_CAP(ID_ISAR6_EL1, BF16, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDBF16),
HWCAP_CAP(ID_ISAR6_EL1, I8MM, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_I8MM),
HWCAP_CAP(ID_PFR2_EL1, SSBS, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SSBS),
#endif
{},
};

14
arch/arm64/kernel/cpuinfo.c
View File

@ -119,6 +119,12 @@ static const char *const hwcap_str[] = {
[KERNEL_HWCAP_CSSC] = "cssc",
[KERNEL_HWCAP_RPRFM] = "rprfm",
[KERNEL_HWCAP_SVE2P1] = "sve2p1",
[KERNEL_HWCAP_SME2] = "sme2",
[KERNEL_HWCAP_SME2P1] = "sme2p1",
[KERNEL_HWCAP_SME_I16I32] = "smei16i32",
[KERNEL_HWCAP_SME_BI32I32] = "smebi32i32",
[KERNEL_HWCAP_SME_B16B16] = "smeb16b16",
[KERNEL_HWCAP_SME_F16F16] = "smef16f16",
};
#ifdef CONFIG_COMPAT
@ -146,6 +152,12 @@ static const char *const compat_hwcap_str[] = {
[COMPAT_KERNEL_HWCAP(VFPD32)] = NULL, /* Not possible on arm64 */
[COMPAT_KERNEL_HWCAP(LPAE)] = "lpae",
[COMPAT_KERNEL_HWCAP(EVTSTRM)] = "evtstrm",
[COMPAT_KERNEL_HWCAP(FPHP)] = "fphp",
[COMPAT_KERNEL_HWCAP(ASIMDHP)] = "asimdhp",
[COMPAT_KERNEL_HWCAP(ASIMDDP)] = "asimddp",
[COMPAT_KERNEL_HWCAP(ASIMDFHM)] = "asimdfhm",
[COMPAT_KERNEL_HWCAP(ASIMDBF16)] = "asimdbf16",
[COMPAT_KERNEL_HWCAP(I8MM)] = "i8mm",
};
#define COMPAT_KERNEL_HWCAP2(x) const_ilog2(COMPAT_HWCAP2_ ## x)
@ -155,6 +167,8 @@ static const char *const compat_hwcap2_str[] = {
[COMPAT_KERNEL_HWCAP2(SHA1)] = "sha1",
[COMPAT_KERNEL_HWCAP2(SHA2)] = "sha2",
[COMPAT_KERNEL_HWCAP2(CRC32)] = "crc32",
[COMPAT_KERNEL_HWCAP2(SB)] = "sb",
[COMPAT_KERNEL_HWCAP2(SSBS)] = "ssbs",
};
#endif /* CONFIG_COMPAT */

30
arch/arm64/kernel/entry-fpsimd.S
View File

@ -100,25 +100,35 @@ SYM_FUNC_START(sme_set_vq)
SYM_FUNC_END(sme_set_vq)
/*
* Save the SME state
* Save the ZA and ZT state
*
* x0 - pointer to buffer for state
* x1 - number of ZT registers to save
*/
SYM_FUNC_START(za_save_state)
_sme_rdsvl 1, 1 // x1 = VL/8
sme_save_za 0, x1, 12
SYM_FUNC_START(sme_save_state)
_sme_rdsvl 2, 1 // x2 = VL/8
sme_save_za 0, x2, 12 // Leaves x0 pointing to the end of ZA
cbz x1, 1f
_str_zt 0
1:
ret
SYM_FUNC_END(za_save_state)
SYM_FUNC_END(sme_save_state)
/*
* Load the SME state
* Load the ZA and ZT state
*
* x0 - pointer to buffer for state
* x1 - number of ZT registers to save
*/
SYM_FUNC_START(za_load_state)
_sme_rdsvl 1, 1 // x1 = VL/8
sme_load_za 0, x1, 12
SYM_FUNC_START(sme_load_state)
_sme_rdsvl 2, 1 // x2 = VL/8
sme_load_za 0, x2, 12 // Leaves x0 pointing to the end of ZA
cbz x1, 1f
_ldr_zt 0
1:
ret
SYM_FUNC_END(za_load_state)
SYM_FUNC_END(sme_load_state)
#endif /* CONFIG_ARM64_SME */

32
arch/arm64/kernel/entry-ftrace.S
View File

@ -65,13 +65,35 @@ SYM_CODE_START(ftrace_caller)
stp x29, x30, [sp, #FREGS_SIZE]
add x29, sp, #FREGS_SIZE
sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
mov x1, x9 // parent_ip (callsite's LR)
ldr_l x2, function_trace_op // op
mov x3, sp // regs
/* Prepare arguments for the the tracer func */
sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
mov x1, x9 // parent_ip (callsite's LR)
mov x3, sp // regs
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
/*
* The literal pointer to the ops is at an 8-byte aligned boundary
* which is either 12 or 16 bytes before the BL instruction in the call
* site. See ftrace_call_adjust() for details.
*
* Therefore here the LR points at `literal + 16` or `literal + 20`,
* and we can find the address of the literal in either case by
* aligning to an 8-byte boundary and subtracting 16. We do the
* alignment first as this allows us to fold the subtraction into the
* LDR.
*/
bic x2, x30, 0x7
ldr x2, [x2, #-16] // op
ldr x4, [x2, #FTRACE_OPS_FUNC] // op->func
blr x4 // op->func(ip, parent_ip, op, regs)
#else
ldr_l x2, function_trace_op // op
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
bl ftrace_stub
bl ftrace_stub // func(ip, parent_ip, op, regs)
#endif
/*
* At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved

41
arch/arm64/kernel/entry.S
View File

@ -275,7 +275,7 @@ alternative_if ARM64_HAS_ADDRESS_AUTH
alternative_else_nop_endif
1:
scs_load tsk
scs_load_current
.else
add x21, sp, #PT_REGS_SIZE
get_current_task tsk
@ -311,13 +311,16 @@ alternative_else_nop_endif
.endif
#ifdef CONFIG_ARM64_PSEUDO_NMI
/* Save pmr */
alternative_if ARM64_HAS_IRQ_PRIO_MASKING
alternative_if_not ARM64_HAS_GIC_PRIO_MASKING
b .Lskip_pmr_save\@
alternative_else_nop_endif
mrs_s x20, SYS_ICC_PMR_EL1
str x20, [sp, #S_PMR_SAVE]
mov x20, #GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET
msr_s SYS_ICC_PMR_EL1, x20
alternative_else_nop_endif
.Lskip_pmr_save\@:
#endif
/*
@ -336,15 +339,19 @@ alternative_else_nop_endif
.endif
#ifdef CONFIG_ARM64_PSEUDO_NMI
/* Restore pmr */
alternative_if ARM64_HAS_IRQ_PRIO_MASKING
alternative_if_not ARM64_HAS_GIC_PRIO_MASKING
b .Lskip_pmr_restore\@
alternative_else_nop_endif
ldr x20, [sp, #S_PMR_SAVE]
msr_s SYS_ICC_PMR_EL1, x20
mrs_s x21, SYS_ICC_CTLR_EL1
tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE
dsb sy // Ensure priority change is seen by redistributor
.L__skip_pmr_sync\@:
/* Ensure priority change is seen by redistributor */
alternative_if_not ARM64_HAS_GIC_PRIO_RELAXED_SYNC
dsb sy
alternative_else_nop_endif
.Lskip_pmr_restore\@:
#endif
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
@ -848,7 +855,7 @@ SYM_FUNC_START(cpu_switch_to)
msr sp_el0, x1
ptrauth_keys_install_kernel x1, x8, x9, x10
scs_save x0
scs_load x1
scs_load_current
ret
SYM_FUNC_END(cpu_switch_to)
NOKPROBE(cpu_switch_to)
@ -876,19 +883,19 @@ NOKPROBE(ret_from_fork)
*/
SYM_FUNC_START(call_on_irq_stack)
#ifdef CONFIG_SHADOW_CALL_STACK
stp scs_sp, xzr, [sp, #-16]!
get_current_task x16
scs_save x16
ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x17
#endif
/* Create a frame record to save our LR and SP (implicit in FP) */
stp x29, x30, [sp, #-16]!
mov x29, sp
ldr_this_cpu x16, irq_stack_ptr, x17
mov x15, #IRQ_STACK_SIZE
add x16, x16, x15
/* Move to the new stack and call the function there */
mov sp, x16
add sp, x16, #IRQ_STACK_SIZE
blr x1
/*
@ -897,9 +904,7 @@ SYM_FUNC_START(call_on_irq_stack)
*/
mov sp, x29
ldp x29, x30, [sp], #16
#ifdef CONFIG_SHADOW_CALL_STACK
ldp scs_sp, xzr, [sp], #16
#endif
scs_load_current
ret
SYM_FUNC_END(call_on_irq_stack)
NOKPROBE(call_on_irq_stack)

52
arch/arm64/kernel/fpsimd.c
View File

@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
/*
* TIF_SME controls whether a task can use SME without trapping while
* in userspace, when TIF_SME is set then we must have storage
* alocated in sve_state and za_state to store the contents of both ZA
* alocated in sve_state and sme_state to store the contents of both ZA
* and the SVE registers for both streaming and non-streaming modes.
*
* If both SVCR.ZA and SVCR.SM are disabled then at any point we
@ -429,7 +429,8 @@ static void task_fpsimd_load(void)
write_sysreg_s(current->thread.svcr, SYS_SVCR);
if (thread_za_enabled(&current->thread))
za_load_state(current->thread.za_state);
sme_load_state(current->thread.sme_state,
system_supports_sme2());
if (thread_sm_enabled(&current->thread))
restore_ffr = system_supports_fa64();
@ -490,7 +491,8 @@ static void fpsimd_save(void)
*svcr = read_sysreg_s(SYS_SVCR);
if (*svcr & SVCR_ZA_MASK)
za_save_state(last->za_state);
sme_save_state(last->sme_state,
system_supports_sme2());
/* If we are in streaming mode override regular SVE. */
if (*svcr & SVCR_SM_MASK) {
@ -1257,30 +1259,30 @@ void fpsimd_release_task(struct task_struct *dead_task)
#ifdef CONFIG_ARM64_SME
/*
* Ensure that task->thread.za_state is allocated and sufficiently large.
* Ensure that task->thread.sme_state is allocated and sufficiently large.
*
* This function should be used only in preparation for replacing
* task->thread.za_state with new data. The memory is always zeroed
* task->thread.sme_state with new data. The memory is always zeroed
* here to prevent stale data from showing through: this is done in
* the interest of testability and predictability, the architecture
* guarantees that when ZA is enabled it will be zeroed.
*/
void sme_alloc(struct task_struct *task)
{
if (task->thread.za_state) {
memset(task->thread.za_state, 0, za_state_size(task));
if (task->thread.sme_state) {
memset(task->thread.sme_state, 0, sme_state_size(task));
return;
}
/* This could potentially be up to 64K. */
task->thread.za_state =
kzalloc(za_state_size(task), GFP_KERNEL);
task->thread.sme_state =
kzalloc(sme_state_size(task), GFP_KERNEL);
}
static void sme_free(struct task_struct *task)
{
kfree(task->thread.za_state);
task->thread.za_state = NULL;
kfree(task->thread.sme_state);
task->thread.sme_state = NULL;
}
void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
@ -1298,6 +1300,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
isb();
}
/*
* This must be called after sme_kernel_enable(), we rely on the
* feature table being sorted to ensure this.
*/
void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
{
/* Allow use of ZT0 */
write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
SYS_SMCR_EL1);
}
/*
* This must be called after sme_kernel_enable(), we rely on the
* feature table being sorted to ensure this.
@ -1322,7 +1335,6 @@ u64 read_smcr_features(void)
unsigned int vq_max;
sme_kernel_enable(NULL);
sme_smstart_sm();
/*
* Set the maximum possible VL.
@ -1332,11 +1344,9 @@ u64 read_smcr_features(void)
smcr = read_sysreg_s(SYS_SMCR_EL1);
smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
vq_max = sve_vq_from_vl(sve_get_vl());
vq_max = sve_vq_from_vl(sme_get_vl());
smcr |= vq_max - 1; /* set LEN field to maximum effective value */
sme_smstop_sm();
return smcr;
}
@ -1488,7 +1498,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
sve_alloc(current, false);
sme_alloc(current);
if (!current->thread.sve_state || !current->thread.za_state) {
if (!current->thread.sve_state || !current->thread.sme_state) {
force_sig(SIGKILL);
return;
}
@ -1609,7 +1619,7 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
void fpsimd_flush_thread(void)
{
void *sve_state = NULL;
void *za_state = NULL;
void *sme_state = NULL;
if (!system_supports_fpsimd())
return;
@ -1634,8 +1644,8 @@ void fpsimd_flush_thread(void)
clear_thread_flag(TIF_SME);
/* Defer kfree() while in atomic context */
za_state = current->thread.za_state;
current->thread.za_state = NULL;
sme_state = current->thread.sme_state;
current->thread.sme_state = NULL;
fpsimd_flush_thread_vl(ARM64_VEC_SME);
current->thread.svcr = 0;
@ -1645,7 +1655,7 @@ void fpsimd_flush_thread(void)
put_cpu_fpsimd_context();
kfree(sve_state);
kfree(za_state);
kfree(sme_state);
}
/*
@ -1711,7 +1721,7 @@ static void fpsimd_bind_task_to_cpu(void)
WARN_ON(!system_supports_fpsimd());
last->st = &current->thread.uw.fpsimd_state;
last->sve_state = current->thread.sve_state;
last->za_state = current->thread.za_state;
last->sme_state = current->thread.sme_state;
last->sve_vl = task_get_sve_vl(current);
last->sme_vl = task_get_sme_vl(current);
last->svcr = &current->thread.svcr;

158
arch/arm64/kernel/ftrace.c
View File

@ -60,6 +60,89 @@ int ftrace_regs_query_register_offset(const char *name)
}
#endif
unsigned long ftrace_call_adjust(unsigned long addr)
{
/*
* When using mcount, addr is the address of the mcount call
* instruction, and no adjustment is necessary.
*/
if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
return addr;
/*
* When using patchable-function-entry without pre-function NOPS, addr
* is the address of the first NOP after the function entry point.
*
* The compiler has either generated:
*
* addr+00: func: NOP // To be patched to MOV X9, LR
* addr+04: NOP // To be patched to BL <caller>
*
* Or:
*
* addr-04: BTI C
* addr+00: func: NOP // To be patched to MOV X9, LR
* addr+04: NOP // To be patched to BL <caller>
*
* We must adjust addr to the address of the NOP which will be patched
* to `BL <caller>`, which is at `addr + 4` bytes in either case.
*
*/
if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
return addr + AARCH64_INSN_SIZE;
/*
* When using patchable-function-entry with pre-function NOPs, addr is
* the address of the first pre-function NOP.
*
* Starting from an 8-byte aligned base, the compiler has either
* generated:
*
* addr+00: NOP // Literal (first 32 bits)
* addr+04: NOP // Literal (last 32 bits)
* addr+08: func: NOP // To be patched to MOV X9, LR
* addr+12: NOP // To be patched to BL <caller>
*
* Or:
*
* addr+00: NOP // Literal (first 32 bits)
* addr+04: NOP // Literal (last 32 bits)
* addr+08: func: BTI C
* addr+12: NOP // To be patched to MOV X9, LR
* addr+16: NOP // To be patched to BL <caller>
*
* We must adjust addr to the address of the NOP which will be patched
* to `BL <caller>`, which is at either addr+12 or addr+16 depending on
* whether there is a BTI.
*/
if (!IS_ALIGNED(addr, sizeof(unsigned long))) {
WARN_RATELIMIT(1, "Misaligned patch-site %pS\n",
(void *)(addr + 8));
return 0;
}
/* Skip the NOPs placed before the function entry point */
addr += 2 * AARCH64_INSN_SIZE;
/* Skip any BTI */
if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
u32 insn = le32_to_cpu(*(__le32 *)addr);
if (aarch64_insn_is_bti(insn)) {
addr += AARCH64_INSN_SIZE;
} else if (insn != aarch64_insn_gen_nop()) {
WARN_RATELIMIT(1, "unexpected insn in patch-site %pS: 0x%08x\n",
(void *)addr, insn);
}
}
/* Skip the first NOP after function entry */
addr += AARCH64_INSN_SIZE;
return addr;
}
/*
* Replace a single instruction, which may be a branch or NOP.
* If @validate == true, a replaced instruction is checked against 'old'.
@ -98,6 +181,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
unsigned long pc;
u32 new;
/*
* When using CALL_OPS, the function to call is associated with the
* call site, and we don't have a global function pointer to update.
*/
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
return 0;
pc = (unsigned long)ftrace_call;
new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
AARCH64_INSN_BRANCH_LINK);
@ -176,6 +266,44 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
return true;
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
static const struct ftrace_ops *arm64_rec_get_ops(struct dyn_ftrace *rec)
{
const struct ftrace_ops *ops = NULL;
if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
ops = ftrace_find_unique_ops(rec);
WARN_ON_ONCE(!ops);
}
if (!ops)
ops = &ftrace_list_ops;
return ops;
}
static int ftrace_rec_set_ops(const struct dyn_ftrace *rec,
const struct ftrace_ops *ops)
{
unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8);
return aarch64_insn_write_literal_u64((void *)literal,
(unsigned long)ops);
}
static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
{
return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
}
static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
{
return ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec));
}
#else
static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
#endif
/*
* Turn on the call to ftrace_caller() in instrumented function
*/
@ -183,6 +311,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old, new;
int ret;
ret = ftrace_rec_update_ops(rec);
if (ret)
return ret;
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
@ -193,6 +326,19 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
return ftrace_modify_code(pc, old, new, true);
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller))
return -EINVAL;
if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller))
return -EINVAL;
return ftrace_rec_update_ops(rec);
}
#endif
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
/*
* The compiler has inserted two NOPs before the regular function prologue.
@ -209,7 +355,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* | NOP | MOV X9, LR | MOV X9, LR |
* | NOP | NOP | BL <entry> |
*
* The LR value will be recovered by ftrace_regs_entry, and restored into LR
* The LR value will be recovered by ftrace_caller, and restored into LR
* before returning to the regular function prologue. When a function is not
* being traced, the MOV is not harmful given x9 is not live per the AAPCS.
*
@ -220,6 +366,11 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
{
unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
u32 old, new;
int ret;
ret = ftrace_rec_set_nop_ops(rec);
if (ret)
return ret;
old = aarch64_insn_gen_nop();
new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
@ -237,9 +388,14 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
{
unsigned long pc = rec->ip;
u32 old = 0, new;
int ret;
new = aarch64_insn_gen_nop();
ret = ftrace_rec_set_nop_ops(rec);
if (ret)
return ret;
/*
* When using mcount, callsites in modules may have been initalized to
* call an arbitrary module PLT (which redirects to the _mcount stub)

116
arch/arm64/kernel/head.S
View File

@ -70,13 +70,14 @@
__EFI_PE_HEADER
__INIT
.section ".idmap.text","a"
/*
* The following callee saved general purpose registers are used on the
* primary lowlevel boot path:
*
* Register Scope Purpose
* x19 primary_entry() .. start_kernel() whether we entered with the MMU on
* x20 primary_entry() .. __primary_switch() CPU boot mode
* x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0
* x22 create_idmap() .. start_kernel() ID map VA of the DT blob
@ -86,10 +87,23 @@
* x28 create_idmap() callee preserved temp register
*/
SYM_CODE_START(primary_entry)
bl record_mmu_state
bl preserve_boot_args
bl create_idmap
/*
* If we entered with the MMU and caches on, clean the ID mapped part
* of the primary boot code to the PoC so we can safely execute it with
* the MMU off.
*/
cbz x19, 0f
adrp x0, __idmap_text_start
adr_l x1, __idmap_text_end
adr_l x2, dcache_clean_poc
blr x2
0: mov x0, x19
bl init_kernel_el // w0=cpu_boot_mode
mov x20, x0
bl create_idmap
/*
* The following calls CPU setup code, see arch/arm64/mm/proc.S for
@ -109,6 +123,40 @@ SYM_CODE_START(primary_entry)
b __primary_switch
SYM_CODE_END(primary_entry)
__INIT
SYM_CODE_START_LOCAL(record_mmu_state)
mrs x19, CurrentEL
cmp x19, #CurrentEL_EL2
mrs x19, sctlr_el1
b.ne 0f
mrs x19, sctlr_el2
0:
CPU_LE( tbnz x19, #SCTLR_ELx_EE_SHIFT, 1f )
CPU_BE( tbz x19, #SCTLR_ELx_EE_SHIFT, 1f )
tst x19, #SCTLR_ELx_C // Z := (C == 0)
and x19, x19, #SCTLR_ELx_M // isolate M bit
csel x19, xzr, x19, eq // clear x19 if Z
ret
/*
* Set the correct endianness early so all memory accesses issued
* before init_kernel_el() occur in the correct byte order. Note that
* this means the MMU must be disabled, or the active ID map will end
* up getting interpreted with the wrong byte order.
*/
1: eor x19, x19, #SCTLR_ELx_EE
bic x19, x19, #SCTLR_ELx_M
b.ne 2f
pre_disable_mmu_workaround
msr sctlr_el2, x19
b 3f
pre_disable_mmu_workaround
2: msr sctlr_el1, x19
3: isb
mov x19, xzr
ret
SYM_CODE_END(record_mmu_state)
/*
* Preserve the arguments passed by the bootloader in x0 .. x3
*/
@ -119,11 +167,14 @@ SYM_CODE_START_LOCAL(preserve_boot_args)
stp x21, x1, [x0] // x0 .. x3 at kernel entry
stp x2, x3, [x0, #16]
cbnz x19, 0f // skip cache invalidation if MMU is on
dmb sy // needed before dc ivac with
// MMU off
add x1, x0, #0x20 // 4 x 8 bytes
b dcache_inval_poc // tail call
0: str_l x19, mmu_enabled_at_boot, x0
ret
SYM_CODE_END(preserve_boot_args)
SYM_FUNC_START_LOCAL(clear_page_tables)
@ -360,12 +411,13 @@ SYM_FUNC_START_LOCAL(create_idmap)
* accesses (MMU disabled), invalidate those tables again to
* remove any speculatively loaded cache lines.
*/
cbnz x19, 0f // skip cache invalidation if MMU is on
dmb sy
adrp x0, init_idmap_pg_dir
adrp x1, init_idmap_pg_end
bl dcache_inval_poc
ret x28
0: ret x28
SYM_FUNC_END(create_idmap)
SYM_FUNC_START_LOCAL(create_kernel_mapping)
@ -404,7 +456,7 @@ SYM_FUNC_END(create_kernel_mapping)
stp xzr, xzr, [sp, #S_STACKFRAME]
add x29, sp, #S_STACKFRAME
scs_load \tsk
scs_load_current
adr_l \tmp1, __per_cpu_offset
ldr w\tmp2, [\tsk, #TSK_TI_CPU]
@ -476,7 +528,7 @@ SYM_FUNC_END(__primary_switched)
* end early head section, begin head code that is also used for
* hotplug and needs to have the same protections as the text region
*/
.section ".idmap.text","awx"
.section ".idmap.text","a"
/*
* Starting from EL2 or EL1, configure the CPU to execute at the highest
@ -489,14 +541,17 @@ SYM_FUNC_END(__primary_switched)
* Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x0 if
* booted in EL1 or EL2 respectively, with the top 32 bits containing
* potential context flags. These flags are *not* stored in __boot_cpu_mode.
*
* x0: whether we are being called from the primary boot path with the MMU on
*/
SYM_FUNC_START(init_kernel_el)
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
mrs x1, CurrentEL
cmp x1, #CurrentEL_EL2
b.eq init_el2
SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
mov_q x0, INIT_SCTLR_EL1_MMU_OFF
pre_disable_mmu_workaround
msr sctlr_el1, x0
isb
mov_q x0, INIT_PSTATE_EL1
@ -506,6 +561,15 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
eret
SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
msr elr_el2, lr
// clean all HYP code to the PoC if we booted at EL2 with the MMU on
cbz x0, 0f
adrp x0, __hyp_idmap_text_start
adr_l x1, __hyp_text_end
adr_l x2, dcache_clean_poc
blr x2
0:
mov_q x0, HCR_HOST_NVHE_FLAGS
msr hcr_el2, x0
isb
@ -529,38 +593,27 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
cbz x0, 1f
/* Set a sane SCTLR_EL1, the VHE way */
pre_disable_mmu_workaround
msr_s SYS_SCTLR_EL12, x1
mov x2, #BOOT_CPU_FLAG_E2H
b 2f
1:
pre_disable_mmu_workaround
msr sctlr_el1, x1
mov x2, xzr
2:
msr elr_el2, lr
mov w0, #BOOT_CPU_MODE_EL2
orr x0, x0, x2
eret
SYM_FUNC_END(init_kernel_el)
/*
* Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
* in w0. See arch/arm64/include/asm/virt.h for more info.
*/
SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag)
adr_l x1, __boot_cpu_mode
cmp w0, #BOOT_CPU_MODE_EL2
b.ne 1f
add x1, x1, #4
1: str w0, [x1] // Save CPU boot mode
ret
SYM_FUNC_END(set_cpu_boot_mode_flag)
/*
* This provides a "holding pen" for platforms to hold all secondary
* cores are held until we're ready for them to initialise.
*/
SYM_FUNC_START(secondary_holding_pen)
mov x0, xzr
bl init_kernel_el // w0=cpu_boot_mode
mrs x2, mpidr_el1
mov_q x1, MPIDR_HWID_BITMASK
@ -578,6 +631,7 @@ SYM_FUNC_END(secondary_holding_pen)
* be used where CPUs are brought online dynamically by the kernel.
*/
SYM_FUNC_START(secondary_entry)
mov x0, xzr
bl init_kernel_el // w0=cpu_boot_mode
b secondary_startup
SYM_FUNC_END(secondary_entry)
@ -587,7 +641,6 @@ SYM_FUNC_START_LOCAL(secondary_startup)
* Common entry point for secondary CPUs.
*/
mov x20, x0 // preserve boot mode
bl finalise_el2
bl __cpu_secondary_check52bitva
#if VA_BITS > 48
ldr_l x0, vabits_actual
@ -600,9 +653,14 @@ SYM_FUNC_START_LOCAL(secondary_startup)
br x8
SYM_FUNC_END(secondary_startup)
.text
SYM_FUNC_START_LOCAL(__secondary_switched)
mov x0, x20
bl set_cpu_boot_mode_flag
mov x0, x20
bl finalise_el2
str_l xzr, __early_cpu_boot_status, x3
adr_l x5, vectors
msr vbar_el1, x5
@ -628,6 +686,19 @@ SYM_FUNC_START_LOCAL(__secondary_too_slow)
b __secondary_too_slow
SYM_FUNC_END(__secondary_too_slow)
/*
* Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
* in w0. See arch/arm64/include/asm/virt.h for more info.
*/
SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag)
adr_l x1, __boot_cpu_mode
cmp w0, #BOOT_CPU_MODE_EL2
b.ne 1f
add x1, x1, #4
1: str w0, [x1] // Save CPU boot mode
ret
SYM_FUNC_END(set_cpu_boot_mode_flag)
/*
* The booting CPU updates the failed status @__early_cpu_boot_status,
* with MMU turned off.
@ -659,6 +730,7 @@ SYM_FUNC_END(__secondary_too_slow)
* Checks if the selected granule size is supported by the CPU.
* If it isn't, park the CPU
*/
.section ".idmap.text","a"
SYM_FUNC_START(__enable_mmu)
mrs x3, ID_AA64MMFR0_EL1
ubfx x3, x3, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4

7
arch/arm64/kernel/hyp-stub.S
View File

@ -132,6 +132,13 @@ SYM_CODE_START_LOCAL(__finalise_el2)
orr x0, x0, SMCR_ELx_FA64_MASK
.Lskip_sme_fa64:
// ZT0 available?
mrs_s x1, SYS_ID_AA64SMFR0_EL1
__check_override id_aa64smfr0 ID_AA64SMFR0_EL1_SMEver_SHIFT 4 .Linit_sme_zt0 .Lskip_sme_zt0
.Linit_sme_zt0:
orr x0, x0, SMCR_ELx_EZT0_MASK
.Lskip_sme_zt0:
orr x0, x0, #SMCR_ELx_LEN_MASK // Enable full SME vector
msr_s SYS_SMCR_EL2, x0 // length for EL1.

1
arch/arm64/kernel/idreg-override.c
View File

@ -131,6 +131,7 @@ static const struct ftr_set_desc smfr0 __initconst = {
.name = "id_aa64smfr0",
.override = &id_aa64smfr0_override,
.fields = {
FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL),
/* FA64 is a one bit field... :-/ */
{ "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, },
{}

7
arch/arm64/kernel/image-vars.h
View File

@ -10,7 +10,7 @@
#error This file should only be included in vmlinux.lds.S
#endif
PROVIDE(__efistub_primary_entry_offset = primary_entry - _text);
PROVIDE(__efistub_primary_entry = primary_entry);
/*
* The EFI stub has its own symbol namespace prefixed by __efistub_, to
@ -21,10 +21,11 @@ PROVIDE(__efistub_primary_entry_offset = primary_entry - _text);
* linked at. The routines below are all implemented in assembler in a
* position independent manner
*/
PROVIDE(__efistub_dcache_clean_poc = __pi_dcache_clean_poc);
PROVIDE(__efistub_caches_clean_inval_pou = __pi_caches_clean_inval_pou);
PROVIDE(__efistub__text = _text);
PROVIDE(__efistub__end = _end);
PROVIDE(__efistub___inittext_end = __inittext_end);
PROVIDE(__efistub__edata = _edata);
PROVIDE(__efistub_screen_info = screen_info);
PROVIDE(__efistub__ctype = _ctype);
@ -67,9 +68,7 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors);
KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
/* Static key checked in pmr_sync(). */
#ifdef CONFIG_ARM64_PSEUDO_NMI
KVM_NVHE_ALIAS(gic_pmr_sync);
/* Static key checked in GIC_PRIO_IRQOFF. */
KVM_NVHE_ALIAS(gic_nonsecure_priorities);
#endif

11
arch/arm64/kernel/patch-scs.c
View File

@ -130,7 +130,8 @@ struct eh_frame {
static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
bool fde_has_augmentation_data,
int code_alignment_factor)
int code_alignment_factor,
bool dry_run)
{
int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
@ -184,7 +185,8 @@ static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
break;
case DW_CFA_negate_ra_state:
scs_patch_loc(loc - 4);
if (!dry_run)
scs_patch_loc(loc - 4);
break;
case 0x40 ... 0x7f:
@ -235,9 +237,12 @@ int noinstr scs_patch(const u8 eh_frame[], int size)
} else {
ret = scs_handle_fde_frame(frame,
fde_has_augmentation_data,
code_alignment_factor);
code_alignment_factor,
true);
if (ret)
return ret;
scs_handle_fde_frame(frame, fde_has_augmentation_data,
code_alignment_factor, false);
}
p += sizeof(frame->size) + frame->size;

17
arch/arm64/kernel/patching.c
View File

@ -88,6 +88,23 @@ int __kprobes aarch64_insn_write(void *addr, u32 insn)
return __aarch64_insn_write(addr, cpu_to_le32(insn));
}
noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val)
{
u64 *waddr;
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&patch_lock, flags);
waddr = patch_map(addr, FIX_TEXT_POKE0);
ret = copy_to_kernel_nofault(waddr, &val, sizeof(val));
patch_unmap(FIX_TEXT_POKE0);
raw_spin_unlock_irqrestore(&patch_lock, flags);
return ret;
}
int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
{
u32 *tp = addr;

4
arch/arm64/kernel/probes/kprobes.c
View File

@ -387,10 +387,6 @@ int __init arch_populate_kprobe_blacklist(void)
(unsigned long)__irqentry_text_end);
if (ret)
return ret;
ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start,
(unsigned long)__idmap_text_end);
if (ret)
return ret;
ret = kprobe_add_area_blacklist((unsigned long)__hyp_text_start,
(unsigned long)__hyp_text_end);
if (ret || is_kernel_in_hyp_mode())

21
arch/arm64/kernel/process.c
View File

@ -307,27 +307,28 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
/*
* In the unlikely event that we create a new thread with ZA
* enabled we should retain the ZA state so duplicate it here.
* This may be shortly freed if we exec() or if CLONE_SETTLS
* but it's simpler to do it here. To avoid confusing the rest
* of the code ensure that we have a sve_state allocated
* whenever za_state is allocated.
* enabled we should retain the ZA and ZT state so duplicate
* it here. This may be shortly freed if we exec() or if
* CLONE_SETTLS but it's simpler to do it here. To avoid
* confusing the rest of the code ensure that we have a
* sve_state allocated whenever sme_state is allocated.
*/
if (thread_za_enabled(&src->thread)) {
dst->thread.sve_state = kzalloc(sve_state_size(src),
GFP_KERNEL);
if (!dst->thread.sve_state)
return -ENOMEM;
dst->thread.za_state = kmemdup(src->thread.za_state,
za_state_size(src),
GFP_KERNEL);
if (!dst->thread.za_state) {
dst->thread.sme_state = kmemdup(src->thread.sme_state,
sme_state_size(src),
GFP_KERNEL);
if (!dst->thread.sme_state) {
kfree(dst->thread.sve_state);
dst->thread.sve_state = NULL;
return -ENOMEM;
}
} else {
dst->thread.za_state = NULL;
dst->thread.sme_state = NULL;
clear_tsk_thread_flag(dst, TIF_SME);
}

64
arch/arm64/kernel/ptrace.c
View File

@ -683,7 +683,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
unsigned long tls[2];
tls[0] = target->thread.uw.tp_value;
if (system_supports_sme())
if (system_supports_tpidr2())
tls[1] = target->thread.tpidr2_el0;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count);
@ -691,7 +691,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
return ret;
target->thread.uw.tp_value = tls[0];
if (system_supports_sme())
if (system_supports_tpidr2())
target->thread.tpidr2_el0 = tls[1];
return ret;
@ -1045,7 +1045,7 @@ static int za_get(struct task_struct *target,
if (thread_za_enabled(&target->thread)) {
start = end;
end = ZA_PT_SIZE(vq);
membuf_write(&to, target->thread.za_state, end - start);
membuf_write(&to, target->thread.sme_state, end - start);
}
/* Zero any trailing padding */
@ -1099,7 +1099,7 @@ static int za_set(struct task_struct *target,
/* Allocate/reinit ZA storage */
sme_alloc(target);
if (!target->thread.za_state) {
if (!target->thread.sme_state) {
ret = -ENOMEM;
goto out;
}
@ -1124,7 +1124,7 @@ static int za_set(struct task_struct *target,
start = ZA_PT_ZA_OFFSET;
end = ZA_PT_SIZE(vq);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
target->thread.za_state,
target->thread.sme_state,
start, end);
if (ret)
goto out;
@ -1138,6 +1138,51 @@ out:
return ret;
}
static int zt_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
{
if (!system_supports_sme2())
return -EINVAL;
/*
* If PSTATE.ZA is not set then ZT will be zeroed when it is
* enabled so report the current register value as zero.
*/
if (thread_za_enabled(&target->thread))
membuf_write(&to, thread_zt_state(&target->thread),
ZT_SIG_REG_BYTES);
else
membuf_zero(&to, ZT_SIG_REG_BYTES);
return 0;
}
static int zt_set(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
int ret;
if (!system_supports_sme2())
return -EINVAL;
if (!thread_za_enabled(&target->thread)) {
sme_alloc(target);
if (!target->thread.sme_state)
return -ENOMEM;
}
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
thread_zt_state(&target->thread),
0, ZT_SIG_REG_BYTES);
if (ret == 0)
target->thread.svcr |= SVCR_ZA_MASK;
return ret;
}
#endif /* CONFIG_ARM64_SME */
#ifdef CONFIG_ARM64_PTR_AUTH
@ -1360,6 +1405,7 @@ enum aarch64_regset {
#ifdef CONFIG_ARM64_SME
REGSET_SSVE,
REGSET_ZA,
REGSET_ZT,
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
REGSET_PAC_MASK,
@ -1467,6 +1513,14 @@ static const struct user_regset aarch64_regsets[] = {
.regset_get = za_get,
.set = za_set,
},
[REGSET_ZT] = { /* SME ZT */
.core_note_type = NT_ARM_ZT,
.n = 1,
.size = ZT_SIG_REG_BYTES,
.align = sizeof(u64),
.regset_get = zt_get,
.set = zt_set,
},
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
[REGSET_PAC_MASK] = {

17
arch/arm64/kernel/setup.c
View File

@ -58,6 +58,7 @@ static int num_standard_resources;
static struct resource *standard_resources;
phys_addr_t __fdt_pointer __initdata;
u64 mmu_enabled_at_boot __initdata;
/*
* Standard memory resources
@ -332,8 +333,12 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
xen_early_init();
efi_init();
if (!efi_enabled(EFI_BOOT) && ((u64)_text % MIN_KIMG_ALIGN) != 0)
pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
if (!efi_enabled(EFI_BOOT)) {
if ((u64)_text % MIN_KIMG_ALIGN)
pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
WARN_TAINT(mmu_enabled_at_boot, TAINT_FIRMWARE_WORKAROUND,
FW_BUG "Booted with MMU enabled!");
}
arm64_memblock_init();
@ -442,3 +447,11 @@ static int __init register_arm64_panic_block(void)
return 0;
}
device_initcall(register_arm64_panic_block);
static int __init check_mmu_enabled_at_boot(void)
{
if (!efi_enabled(EFI_BOOT) && mmu_enabled_at_boot)
panic("Non-EFI boot detected with MMU and caches enabled");
return 0;
}
device_initcall_sync(check_mmu_enabled_at_boot);

261
arch/arm64/kernel/signal.c
View File

@ -56,7 +56,9 @@ struct rt_sigframe_user_layout {
unsigned long fpsimd_offset;
unsigned long esr_offset;
unsigned long sve_offset;
unsigned long tpidr2_offset;
unsigned long za_offset;
unsigned long zt_offset;
unsigned long extra_offset;
unsigned long end_offset;
};
@ -168,6 +170,19 @@ static void __user *apply_user_offset(
return base + offset;
}
struct user_ctxs {
struct fpsimd_context __user *fpsimd;
u32 fpsimd_size;
struct sve_context __user *sve;
u32 sve_size;
struct tpidr2_context __user *tpidr2;
u32 tpidr2_size;
struct za_context __user *za;
u32 za_size;
struct zt_context __user *zt;
u32 zt_size;
};
static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
{
struct user_fpsimd_state const *fpsimd =
@ -186,25 +201,20 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
return err ? -EFAULT : 0;
}
static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
static int restore_fpsimd_context(struct user_ctxs *user)
{
struct user_fpsimd_state fpsimd;
__u32 magic, size;
int err = 0;
/* check the magic/size information */
__get_user_error(magic, &ctx->head.magic, err);
__get_user_error(size, &ctx->head.size, err);
if (err)
return -EFAULT;
if (magic != FPSIMD_MAGIC || size != sizeof(struct fpsimd_context))
/* check the size information */
if (user->fpsimd_size != sizeof(struct fpsimd_context))
return -EINVAL;
/* copy the FP and status/control registers */
err = __copy_from_user(fpsimd.vregs, ctx->vregs,
err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs),
sizeof(fpsimd.vregs));
__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
__get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err);
__get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err);
clear_thread_flag(TIF_SVE);
current->thread.fp_type = FP_STATE_FPSIMD;
@ -217,12 +227,6 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
}
struct user_ctxs {
struct fpsimd_context __user *fpsimd;
struct sve_context __user *sve;
struct za_context __user *za;
};
#ifdef CONFIG_ARM64_SVE
static int preserve_sve_context(struct sve_context __user *ctx)
@ -267,15 +271,20 @@ static int preserve_sve_context(struct sve_context __user *ctx)
static int restore_sve_fpsimd_context(struct user_ctxs *user)
{
int err;
int err = 0;
unsigned int vl, vq;
struct user_fpsimd_state fpsimd;
struct sve_context sve;
u16 user_vl, flags;
if (__copy_from_user(&sve, user->sve, sizeof(sve)))
return -EFAULT;
if (user->sve_size < sizeof(*user->sve))
return -EINVAL;
if (sve.flags & SVE_SIG_FLAG_SM) {
__get_user_error(user_vl, &(user->sve->vl), err);
__get_user_error(flags, &(user->sve->flags), err);
if (err)
return err;
if (flags & SVE_SIG_FLAG_SM) {
if (!system_supports_sme())
return -EINVAL;
@ -292,19 +301,19 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
vl = task_get_sve_vl(current);
}
if (sve.vl != vl)
if (user_vl != vl)
return -EINVAL;
if (sve.head.size <= sizeof(*user->sve)) {
if (user->sve_size == sizeof(*user->sve)) {
clear_thread_flag(TIF_SVE);
current->thread.svcr &= ~SVCR_SM_MASK;
current->thread.fp_type = FP_STATE_FPSIMD;
goto fpsimd_only;
}
vq = sve_vq_from_vl(sve.vl);
vq = sve_vq_from_vl(vl);
if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
/*
@ -330,7 +339,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
if (err)
return -EFAULT;
if (sve.flags & SVE_SIG_FLAG_SM)
if (flags & SVE_SIG_FLAG_SM)
current->thread.svcr |= SVCR_SM_MASK;
else
set_thread_flag(TIF_SVE);
@ -366,6 +375,34 @@ extern int preserve_sve_context(void __user *ctx);
#ifdef CONFIG_ARM64_SME
static int preserve_tpidr2_context(struct tpidr2_context __user *ctx)
{
int err = 0;
current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
__put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
__put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err);
return err;
}
static int restore_tpidr2_context(struct user_ctxs *user)
{
u64 tpidr2_el0;
int err = 0;
if (user->tpidr2_size != sizeof(*user->tpidr2))
return -EINVAL;
__get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err);
if (!err)
current->thread.tpidr2_el0 = tpidr2_el0;
return err;
}
static int preserve_za_context(struct za_context __user *ctx)
{
int err = 0;
@ -394,7 +431,7 @@ static int preserve_za_context(struct za_context __user *ctx)
* fpsimd_signal_preserve_current_state().
*/
err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
current->thread.za_state,
current->thread.sme_state,
ZA_SIG_REGS_SIZE(vq));
}
@ -403,29 +440,33 @@ static int preserve_za_context(struct za_context __user *ctx)
static int restore_za_context(struct user_ctxs *user)
{
int err;
int err = 0;
unsigned int vq;
struct za_context za;
u16 user_vl;
if (__copy_from_user(&za, user->za, sizeof(za)))
return -EFAULT;
if (za.vl != task_get_sme_vl(current))
if (user->za_size < sizeof(*user->za))
return -EINVAL;
if (za.head.size <= sizeof(*user->za)) {
__get_user_error(user_vl, &(user->za->vl), err);
if (err)
return err;
if (user_vl != task_get_sme_vl(current))
return -EINVAL;
if (user->za_size == sizeof(*user->za)) {
current->thread.svcr &= ~SVCR_ZA_MASK;
return 0;
}
vq = sve_vq_from_vl(za.vl);
vq = sve_vq_from_vl(user_vl);
if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq))
if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
/*
* Careful: we are about __copy_from_user() directly into
* thread.za_state with preemption enabled, so protection is
* thread.sme_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
@ -434,13 +475,13 @@ static int restore_za_context(struct user_ctxs *user)
/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
sme_alloc(current);
if (!current->thread.za_state) {
if (!current->thread.sme_state) {
current->thread.svcr &= ~SVCR_ZA_MASK;
clear_thread_flag(TIF_SME);
return -ENOMEM;
}
err = __copy_from_user(current->thread.za_state,
err = __copy_from_user(current->thread.sme_state,
(char __user const *)user->za +
ZA_SIG_REGS_OFFSET,
ZA_SIG_REGS_SIZE(vq));
@ -452,11 +493,83 @@ static int restore_za_context(struct user_ctxs *user)
return 0;
}
static int preserve_zt_context(struct zt_context __user *ctx)
{
int err = 0;
u16 reserved[ARRAY_SIZE(ctx->__reserved)];
if (WARN_ON(!thread_za_enabled(&current->thread)))
return -EINVAL;
memset(reserved, 0, sizeof(reserved));
__put_user_error(ZT_MAGIC, &ctx->head.magic, err);
__put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16),
&ctx->head.size, err);
__put_user_error(1, &ctx->nregs, err);
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
/*
* This assumes that the ZT state has already been saved to
* the task struct by calling the function
* fpsimd_signal_preserve_current_state().
*/
err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
thread_zt_state(&current->thread),
ZT_SIG_REGS_SIZE(1));
return err ? -EFAULT : 0;
}
static int restore_zt_context(struct user_ctxs *user)
{
int err;
u16 nregs;
/* ZA must be restored first for this check to be valid */
if (!thread_za_enabled(&current->thread))
return -EINVAL;
if (user->zt_size != ZT_SIG_CONTEXT_SIZE(1))
return -EINVAL;
if (__copy_from_user(&nregs, &(user->zt->nregs), sizeof(nregs)))
return -EFAULT;
if (nregs != 1)
return -EINVAL;
/*
* Careful: we are about __copy_from_user() directly into
* thread.zt_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
fpsimd_flush_task_state(current);
/* From now, fpsimd_thread_switch() won't touch ZT in thread state */
err = __copy_from_user(thread_zt_state(&current->thread),
(char __user const *)user->zt +
ZT_SIG_REGS_OFFSET,
ZT_SIG_REGS_SIZE(1));
if (err)
return -EFAULT;
return 0;
}
#else /* ! CONFIG_ARM64_SME */
/* Turn any non-optimised out attempts to use these into a link error: */
extern int preserve_tpidr2_context(void __user *ctx);
extern int restore_tpidr2_context(struct user_ctxs *user);
extern int preserve_za_context(void __user *ctx);
extern int restore_za_context(struct user_ctxs *user);
extern int preserve_zt_context(void __user *ctx);
extern int restore_zt_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_SME */
@ -473,7 +586,9 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->fpsimd = NULL;
user->sve = NULL;
user->tpidr2 = NULL;
user->za = NULL;
user->zt = NULL;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
@ -516,10 +631,8 @@ static int parse_user_sigframe(struct user_ctxs *user,
if (user->fpsimd)
goto invalid;
if (size < sizeof(*user->fpsimd))
goto invalid;
user->fpsimd = (struct fpsimd_context __user *)head;
user->fpsimd_size = size;
break;
case ESR_MAGIC:
@ -533,10 +646,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
if (user->sve)
goto invalid;
if (size < sizeof(*user->sve))
user->sve = (struct sve_context __user *)head;
user->sve_size = size;
break;
case TPIDR2_MAGIC:
if (!system_supports_sme())
goto invalid;
user->sve = (struct sve_context __user *)head;
if (user->tpidr2)
goto invalid;
user->tpidr2 = (struct tpidr2_context __user *)head;
user->tpidr2_size = size;
break;
case ZA_MAGIC:
@ -546,10 +668,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
if (user->za)
goto invalid;
if (size < sizeof(*user->za))
user->za = (struct za_context __user *)head;
user->za_size = size;
break;
case ZT_MAGIC:
if (!system_supports_sme2())
goto invalid;
user->za = (struct za_context __user *)head;
if (user->zt)
goto invalid;
user->zt = (struct zt_context __user *)head;
user->zt_size = size;
break;
case EXTRA_MAGIC:
@ -668,12 +799,18 @@ static int restore_sigframe(struct pt_regs *regs,
if (user.sve)
err = restore_sve_fpsimd_context(&user);
else
err = restore_fpsimd_context(user.fpsimd);
err = restore_fpsimd_context(&user);
}
if (err == 0 && system_supports_sme() && user.tpidr2)
err = restore_tpidr2_context(&user);
if (err == 0 && system_supports_sme() && user.za)
err = restore_za_context(&user);
if (err == 0 && system_supports_sme2() && user.zt)
err = restore_zt_context(&user);
return err;
}
@ -765,6 +902,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
else
vl = task_get_sme_vl(current);
err = sigframe_alloc(user, &user->tpidr2_offset,
sizeof(struct tpidr2_context));
if (err)
return err;
if (thread_za_enabled(&current->thread))
vq = sve_vq_from_vl(vl);
@ -774,6 +916,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
return err;
}
if (system_supports_sme2()) {
if (add_all || thread_za_enabled(&current->thread)) {
err = sigframe_alloc(user, &user->zt_offset,
ZT_SIG_CONTEXT_SIZE(1));
if (err)
return err;
}
}
return sigframe_alloc_end(user);
}
@ -822,6 +973,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
err |= preserve_sve_context(sve_ctx);
}
/* TPIDR2 if supported */
if (system_supports_sme() && err == 0) {
struct tpidr2_context __user *tpidr2_ctx =
apply_user_offset(user, user->tpidr2_offset);
err |= preserve_tpidr2_context(tpidr2_ctx);
}
/* ZA state if present */
if (system_supports_sme() && err == 0 && user->za_offset) {
struct za_context __user *za_ctx =
@ -829,6 +987,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
err |= preserve_za_context(za_ctx);
}
/* ZT state if present */
if (system_supports_sme2() && err == 0 && user->zt_offset) {
struct zt_context __user *zt_ctx =
apply_user_offset(user, user->zt_offset);
err |= preserve_zt_context(zt_ctx);
}
if (err == 0 && user->extra_offset) {
char __user *sfp = (char __user *)user->sigframe;
char __user *userp =

6
arch/arm64/kernel/sleep.S
View File

@ -99,8 +99,9 @@ SYM_FUNC_END(__cpu_suspend_enter)
.pushsection ".idmap.text", "awx"
SYM_CODE_START(cpu_resume)
mov x0, xzr
bl init_kernel_el
bl finalise_el2
mov x19, x0 // preserve boot mode
#if VA_BITS > 48
ldr_l x0, vabits_actual
#endif
@ -116,6 +117,9 @@ SYM_CODE_END(cpu_resume)
.popsection
SYM_FUNC_START(_cpu_resume)
mov x0, x19
bl finalise_el2
mrs x1, mpidr_el1
adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt address

8
arch/arm64/kernel/syscall.c
View File

@ -173,12 +173,8 @@ static inline void fp_user_discard(void)
* register state to track, if this changes the KVM code will
* need updating.
*/
if (system_supports_sme() && test_thread_flag(TIF_SME)) {
u64 svcr = read_sysreg_s(SYS_SVCR);
if (svcr & SVCR_SM_MASK)
sme_smstop_sm();
}
if (system_supports_sme())
sme_smstop_sm();
if (!system_supports_sve())
return;

6
arch/arm64/kernel/traps.c
View File

@ -163,10 +163,8 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
if (!bad)
p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val);
else {
p += sprintf(p, "bad PC value");
break;
}
else
p += sprintf(p, i == 0 ? "(????????) " : "???????? ");
}
printk("%sCode: %s\n", lvl, str);

8
arch/arm64/kernel/vmlinux.lds.S
View File

@ -93,6 +93,7 @@ jiffies = jiffies_64;
#ifdef CONFIG_HIBERNATION
#define HIBERNATE_TEXT \
ALIGN_FUNCTION(); \
__hibernate_exit_text_start = .; \
*(.hibernate_exit.text) \
__hibernate_exit_text_end = .;
@ -102,6 +103,7 @@ jiffies = jiffies_64;
#ifdef CONFIG_KEXEC_CORE
#define KEXEC_TEXT \
ALIGN_FUNCTION(); \
__relocate_new_kernel_start = .; \
*(.kexec_relocate.text) \
__relocate_new_kernel_end = .;
@ -178,7 +180,6 @@ SECTIONS
LOCK_TEXT
KPROBES_TEXT
HYPERVISOR_TEXT
IDMAP_TEXT
*(.gnu.warning)
. = ALIGN(16);
*(.got) /* Global offset table */
@ -205,6 +206,7 @@ SECTIONS
TRAMP_TEXT
HIBERNATE_TEXT
KEXEC_TEXT
IDMAP_TEXT
. = ALIGN(PAGE_SIZE);
}
@ -354,6 +356,8 @@ ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
#ifdef CONFIG_HIBERNATION
ASSERT(__hibernate_exit_text_end - __hibernate_exit_text_start <= SZ_4K,
"Hibernate exit text is bigger than 4 KiB")
ASSERT(__hibernate_exit_text_start == swsusp_arch_suspend_exit,
"Hibernate exit text does not start with swsusp_arch_suspend_exit")
#endif
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE,
@ -380,4 +384,6 @@ ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET,
ASSERT(__relocate_new_kernel_end - __relocate_new_kernel_start <= SZ_4K,
"kexec relocation code is bigger than 4 KiB")
ASSERT(KEXEC_CONTROL_PAGE_SIZE >= SZ_4K, "KEXEC_CONTROL_PAGE_SIZE is broken")
ASSERT(__relocate_new_kernel_start == arm64_relocate_new_kernel,
"kexec control page does not start with arm64_relocate_new_kernel")
#endif

2
arch/arm64/kvm/debug.c
View File

@ -328,7 +328,7 @@ void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu)
* we may need to check if the host state needs to be saved.
*/
if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) &&
!(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(SYS_PMBIDR_EL1_P_SHIFT)))
!(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT)))
vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE);
/* Check if we have TRBE implemented and available at the host */

2
arch/arm64/kvm/fpsimd.c
View File

@ -143,7 +143,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
fp_state.st = &vcpu->arch.ctxt.fp_regs;
fp_state.sve_state = vcpu->arch.sve_state;
fp_state.sve_vl = vcpu->arch.sve_max_vl;
fp_state.za_state = NULL;
fp_state.sme_state = NULL;
fp_state.svcr = &vcpu->arch.svcr;
fp_state.fp_type = &vcpu->arch.fp_type;

2
arch/arm64/kvm/hyp/entry.S
View File

@ -171,7 +171,7 @@ alternative_else
dsb sy // Synchronize against in-flight ld/st
isb // Prevent an early read of side-effect free ISR
mrs x2, isr_el1
tbnz x2, #8, 2f // ISR_EL1.A
tbnz x2, #ISR_EL1_A_SHIFT, 2f
ret
nop
2:

2
arch/arm64/kvm/hyp/nvhe/debug-sr.c
View File

@ -27,7 +27,7 @@ static void __debug_save_spe(u64 *pmscr_el1)
* Check if the host is actually using it ?
*/
reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
if (!(reg & BIT(PMBLIMITR_EL1_E_SHIFT)))
return;
/* Yes; save the control register and disable data generation */

1
arch/arm64/mm/cache.S
View File

@ -56,6 +56,7 @@ SYM_FUNC_START(caches_clean_inval_pou)
caches_clean_inval_pou_macro
ret
SYM_FUNC_END(caches_clean_inval_pou)
SYM_FUNC_ALIAS(__pi_caches_clean_inval_pou, caches_clean_inval_pou)
/*
* caches_clean_inval_user_pou(start,end)

8
arch/arm64/mm/mmu.c
View File

@ -133,7 +133,7 @@ static phys_addr_t __init early_pgtable_alloc(int shift)
return phys;
}
static bool pgattr_change_is_safe(u64 old, u64 new)
bool pgattr_change_is_safe(u64 old, u64 new)
{
/*
* The following mapping attributes may be updated in live
@ -142,9 +142,13 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
/* creating or taking down mappings is always safe */
if (old == 0 || new == 0)
if (!pte_valid(__pte(old)) || !pte_valid(__pte(new)))
return true;
/* A live entry's pfn should not change */
if (pte_pfn(__pte(old)) != pte_pfn(__pte(new)))
return false;
/* live contiguous mappings may not be manipulated at all */
if ((old | new) & PTE_CONT)
return false;

2
arch/arm64/mm/proc.S
View File

@ -110,7 +110,6 @@ SYM_FUNC_END(cpu_do_suspend)
*
* x0: Address of context pointer
*/
.pushsection ".idmap.text", "awx"
SYM_FUNC_START(cpu_do_resume)
ldp x2, x3, [x0]
ldp x4, x5, [x0, #16]
@ -166,7 +165,6 @@ alternative_else_nop_endif
isb
ret
SYM_FUNC_END(cpu_do_resume)
.popsection
#endif
.pushsection ".idmap.text", "awx"

6
arch/arm64/tools/cpucaps
View File

@ -28,7 +28,9 @@ HAS_GENERIC_AUTH
HAS_GENERIC_AUTH_ARCH_QARMA3
HAS_GENERIC_AUTH_ARCH_QARMA5
HAS_GENERIC_AUTH_IMP_DEF
HAS_IRQ_PRIO_MASKING
HAS_GIC_CPUIF_SYSREGS
HAS_GIC_PRIO_MASKING
HAS_GIC_PRIO_RELAXED_SYNC
HAS_LDAPR
HAS_LSE_ATOMICS
HAS_NO_FPSIMD
@ -38,7 +40,6 @@ HAS_RAS_EXTN
HAS_RNG
HAS_SB
HAS_STAGE2_FWB
HAS_SYSREG_GIC_CPUIF
HAS_TIDCP1
HAS_TLB_RANGE
HAS_VIRT_HOST_EXTN
@ -50,6 +51,7 @@ MTE
MTE_ASYMM
SME
SME_FA64
SME2
SPECTRE_V2
SPECTRE_V3A
SPECTRE_V4

29
arch/arm64/tools/gen-sysreg.awk
View File

@ -44,6 +44,11 @@ function define_field(reg, field, msb, lsb) {
define(reg "_" field "_WIDTH", msb - lsb + 1)
}
# Print a field _SIGNED definition for a field
function define_field_sign(reg, field, sign) {
define(reg "_" field "_SIGNED", sign)
}
# Parse a "<msb>[:<lsb>]" string into the global variables @msb and @lsb
function parse_bitdef(reg, field, bitdef, _bits)
{
@ -233,6 +238,30 @@ END {
next
}
/^SignedEnum/ {
change_block("Enum<", "Sysreg", "Enum")
expect_fields(3)
field = $3
parse_bitdef(reg, field, $2)
define_field(reg, field, msb, lsb)
define_field_sign(reg, field, "true")
next
}
/^UnsignedEnum/ {
change_block("Enum<", "Sysreg", "Enum")
expect_fields(3)
field = $3
parse_bitdef(reg, field, $2)
define_field(reg, field, msb, lsb)
define_field_sign(reg, field, "false")
next
}
/^Enum/ {
change_block("Enum", "Sysreg", "Enum")
expect_fields(3)

560
arch/arm64/tools/sysreg
View File

File diff suppressed because it is too large Load Diff

2
drivers/acpi/acpica/Makefile
View File

@ -3,7 +3,7 @@
# Makefile for ACPICA Core interpreter
#
ccflags-y := -Os -D_LINUX -DBUILDING_ACPICA
ccflags-y := -D_LINUX -DBUILDING_ACPICA
ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT
# use acpi.o to put all files here into acpi.o modparam namespace

4
drivers/firmware/efi/libstub/Makefile
View File

@ -87,7 +87,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB) += efi-stub.o string.o intrinsics.o systable.o \
screen_info.o efi-stub-entry.o
lib-$(CONFIG_ARM) += arm32-stub.o
lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o arm64-entry.o smbios.o
lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o smbios.o
lib-$(CONFIG_X86) += x86-stub.o
lib-$(CONFIG_RISCV) += riscv.o riscv-stub.o
lib-$(CONFIG_LOONGARCH) += loongarch.o loongarch-stub.o
@ -141,7 +141,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM) := R_ARM_ABS
#
STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \
--prefix-symbols=__efistub_
STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS64
STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS
# For RISC-V, we don't need anything special other than arm64. Keep all the
# symbols in .init section and make sure that no absolute symbols references

67
drivers/firmware/efi/libstub/arm64-entry.S
View File

@ -1,67 +0,0 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* EFI entry point.
*
* Copyright (C) 2013, 2014 Red Hat, Inc.
* Author: Mark Salter <msalter@redhat.com>
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
/*
* The entrypoint of a arm64 bare metal image is at offset #0 of the
* image, so this is a reasonable default for primary_entry_offset.
* Only when the EFI stub is integrated into the core kernel, it is not
* guaranteed that the PE/COFF header has been copied to memory too, so
* in this case, primary_entry_offset should be overridden by the
* linker and point to primary_entry() directly.
*/
.weak primary_entry_offset
SYM_CODE_START(efi_enter_kernel)
/*
* efi_pe_entry() will have copied the kernel image if necessary and we
* end up here with device tree address in x1 and the kernel entry
* point stored in x0. Save those values in registers which are
* callee preserved.
*/
ldr w2, =primary_entry_offset
add x19, x0, x2 // relocated Image entrypoint
mov x0, x1 // DTB address
mov x1, xzr
mov x2, xzr
mov x3, xzr
/*
* Clean the remainder of this routine to the PoC
* so that we can safely disable the MMU and caches.
*/
adr x4, 1f
dc civac, x4
dsb sy
/* Turn off Dcache and MMU */
mrs x4, CurrentEL
cmp x4, #CurrentEL_EL2
mrs x4, sctlr_el1
b.ne 0f
mrs x4, sctlr_el2
0: bic x4, x4, #SCTLR_ELx_M
bic x4, x4, #SCTLR_ELx_C
b.eq 1f
b 2f
.balign 32
1: pre_disable_mmu_workaround
msr sctlr_el2, x4
isb
br x19 // jump to kernel entrypoint
2: pre_disable_mmu_workaround
msr sctlr_el1, x4
isb
br x19 // jump to kernel entrypoint
.org 1b + 32
SYM_CODE_END(efi_enter_kernel)

28
drivers/firmware/efi/libstub/arm64-stub.c
View File

@ -58,7 +58,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
efi_handle_t image_handle)
{
efi_status_t status;
unsigned long kernel_size, kernel_memsize = 0;
unsigned long kernel_size, kernel_codesize, kernel_memsize;
u32 phys_seed = 0;
u64 min_kimg_align = efi_get_kimg_min_align();
@ -93,6 +93,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
SEGMENT_ALIGN >> 10);
kernel_size = _edata - _text;
kernel_codesize = __inittext_end - _text;
kernel_memsize = kernel_size + (_end - _edata);
*reserve_size = kernel_memsize;
@ -121,7 +122,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
*/
*image_addr = (u64)_text;
*reserve_size = 0;
goto clean_image_to_poc;
return EFI_SUCCESS;
}
status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
@ -137,14 +138,21 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
*image_addr = *reserve_addr;
memcpy((void *)*image_addr, _text, kernel_size);
clean_image_to_poc:
/*
* Clean the copied Image to the PoC, and ensure it is not shadowed by
* stale icache entries from before relocation.
*/
dcache_clean_poc(*image_addr, *image_addr + kernel_size);
asm("ic ialluis");
caches_clean_inval_pou(*image_addr, *image_addr + kernel_codesize);
return EFI_SUCCESS;
}
asmlinkage void primary_entry(void);
unsigned long primary_entry_offset(void)
{
/*
* When built as part of the kernel, the EFI stub cannot branch to the
* kernel proper via the image header, as the PE/COFF header is
* strictly not part of the in-memory presentation of the image, only
* of the file representation. So instead, we need to jump to the
* actual entrypoint in the .text region of the image.
*/
return (char *)primary_entry - _text;
}

41
drivers/firmware/efi/libstub/arm64.c
View File

@ -59,6 +59,12 @@ efi_status_t check_platform_features(void)
return EFI_SUCCESS;
}
#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
#define DCTYPE "civac"
#else
#define DCTYPE "cvau"
#endif
void efi_cache_sync_image(unsigned long image_base,
unsigned long alloc_size,
unsigned long code_size)
@ -67,13 +73,38 @@ void efi_cache_sync_image(unsigned long image_base,
u64 lsize = 4 << cpuid_feature_extract_unsigned_field(ctr,
CTR_EL0_DminLine_SHIFT);
do {
asm("dc civac, %0" :: "r"(image_base));
image_base += lsize;
alloc_size -= lsize;
} while (alloc_size >= lsize);
/* only perform the cache maintenance if needed for I/D coherency */
if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) {
do {
asm("dc " DCTYPE ", %0" :: "r"(image_base));
image_base += lsize;
code_size -= lsize;
} while (code_size >= lsize);
}
asm("ic ialluis");
dsb(ish);
isb();
}
unsigned long __weak primary_entry_offset(void)
{
/*
* By default, we can invoke the kernel via the branch instruction in
* the image header, so offset #0. This will be overridden by the EFI
* stub build that is linked into the core kernel, as in that case, the
* image header may not have been loaded into memory, or may be mapped
* with non-executable permissions.
*/
return 0;
}
void __noreturn efi_enter_kernel(unsigned long entrypoint,
unsigned long fdt_addr,
unsigned long fdt_size)
{
void (* __noreturn enter_kernel)(u64, u64, u64, u64);
enter_kernel = (void *)entrypoint + primary_entry_offset();
enter_kernel(fdt_addr, 0, 0, 0);
}

19
drivers/irqchip/irq-gic-v3.c
View File

@ -89,15 +89,6 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
*/
static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
/*
* Global static key controlling whether an update to PMR allowing more
* interrupts requires to be propagated to the redistributor (DSB SY).
* And this needs to be exported for modules to be able to enable
* interrupts...
*/
DEFINE_STATIC_KEY_FALSE(gic_pmr_sync);
EXPORT_SYMBOL(gic_pmr_sync);
DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities);
EXPORT_SYMBOL(gic_nonsecure_priorities);
@ -1766,16 +1757,8 @@ static void gic_enable_nmi_support(void)
for (i = 0; i < gic_data.ppi_nr; i++)
refcount_set(&ppi_nmi_refs[i], 0);
/*
* Linux itself doesn't use 1:N distribution, so has no need to
* set PMHE. The only reason to have it set is if EL3 requires it
* (and we can't change it).
*/
if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK)
static_branch_enable(&gic_pmr_sync);
pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n",
static_branch_unlikely(&gic_pmr_sync) ? "forced" : "relaxed");
gic_has_relaxed_pmr_sync() ? "relaxed" : "forced");
/*
* How priority values are used by the GIC depends on two things:

2
drivers/irqchip/irq-gic.c
View File

@ -54,7 +54,7 @@
static void gic_check_cpu_features(void)
{
WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_GIC_CPUIF_SYSREGS),
TAINT_CPU_OUT_OF_SPEC,
"GICv3 system registers enabled, broken firmware!\n");
}

1
drivers/perf/arm-cmn.c
View File

@ -1870,6 +1870,7 @@ static void arm_cmn_init_dtm(struct arm_cmn_dtm *dtm, struct arm_cmn_node *xp, i
dtm->base = xp->pmu_base + CMN_DTM_OFFSET(idx);
dtm->pmu_config_low = CMN_DTM_PMU_CONFIG_PMU_EN;
writeq_relaxed(dtm->pmu_config_low, dtm->base + CMN_DTM_PMU_CONFIG);
for (i = 0; i < 4; i++) {
dtm->wp_event[i] = -1;
writeq_relaxed(0, dtm->base + CMN_DTM_WPn_MASK(i));

160
drivers/perf/arm_spe_pmu.c
View File

@ -12,6 +12,7 @@
#define DRVNAME PMUNAME "_pmu"
#define pr_fmt(fmt) DRVNAME ": " fmt
#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <linux/bug.h>
#include <linux/capability.h>
@ -84,6 +85,7 @@ struct arm_spe_pmu {
#define SPE_PMU_FEAT_ARCH_INST (1UL << 3)
#define SPE_PMU_FEAT_LDS (1UL << 4)
#define SPE_PMU_FEAT_ERND (1UL << 5)
#define SPE_PMU_FEAT_INV_FILT_EVT (1UL << 6)
#define SPE_PMU_FEAT_DEV_PROBED (1UL << 63)
u64 features;
@ -201,6 +203,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
#define ATTR_CFG_FLD_min_latency_LO 0
#define ATTR_CFG_FLD_min_latency_HI 11
#define ATTR_CFG_FLD_inv_event_filter_CFG config3 /* PMSNEVFR_EL1 */
#define ATTR_CFG_FLD_inv_event_filter_LO 0
#define ATTR_CFG_FLD_inv_event_filter_HI 63
/* Why does everything I do descend into this? */
#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \
(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
@ -231,6 +237,7 @@ GEN_PMU_FORMAT_ATTR(branch_filter);
GEN_PMU_FORMAT_ATTR(load_filter);
GEN_PMU_FORMAT_ATTR(store_filter);
GEN_PMU_FORMAT_ATTR(event_filter);
GEN_PMU_FORMAT_ATTR(inv_event_filter);
GEN_PMU_FORMAT_ATTR(min_latency);
static struct attribute *arm_spe_pmu_formats_attr[] = {
@ -242,12 +249,27 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
&format_attr_load_filter.attr,
&format_attr_store_filter.attr,
&format_attr_event_filter.attr,
&format_attr_inv_event_filter.attr,
&format_attr_min_latency.attr,
NULL,
};
static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj,
struct attribute *attr,
int unused)
{
struct device *dev = kobj_to_dev(kobj);
struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
return 0;
return attr->mode;
}
static const struct attribute_group arm_spe_pmu_format_group = {
.name = "format",
.is_visible = arm_spe_pmu_format_attr_is_visible,
.attrs = arm_spe_pmu_formats_attr,
};
@ -282,18 +304,18 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event)
struct perf_event_attr *attr = &event->attr;
u64 reg = 0;
reg |= ATTR_CFG_GET_FLD(attr, ts_enable) << SYS_PMSCR_EL1_TS_SHIFT;
reg |= ATTR_CFG_GET_FLD(attr, pa_enable) << SYS_PMSCR_EL1_PA_SHIFT;
reg |= ATTR_CFG_GET_FLD(attr, pct_enable) << SYS_PMSCR_EL1_PCT_SHIFT;
reg |= FIELD_PREP(PMSCR_EL1_TS, ATTR_CFG_GET_FLD(attr, ts_enable));
reg |= FIELD_PREP(PMSCR_EL1_PA, ATTR_CFG_GET_FLD(attr, pa_enable));
reg |= FIELD_PREP(PMSCR_EL1_PCT, ATTR_CFG_GET_FLD(attr, pct_enable));
if (!attr->exclude_user)
reg |= BIT(SYS_PMSCR_EL1_E0SPE_SHIFT);
reg |= PMSCR_EL1_E0SPE;
if (!attr->exclude_kernel)
reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT);
reg |= PMSCR_EL1_E1SPE;
if (get_spe_event_has_cx(event))
reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT);
reg |= PMSCR_EL1_CX;
return reg;
}
@ -302,8 +324,7 @@ static void arm_spe_event_sanitise_period(struct perf_event *event)
{
struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu);
u64 period = event->hw.sample_period;
u64 max_period = SYS_PMSIRR_EL1_INTERVAL_MASK
<< SYS_PMSIRR_EL1_INTERVAL_SHIFT;
u64 max_period = PMSIRR_EL1_INTERVAL_MASK;
if (period < spe_pmu->min_period)
period = spe_pmu->min_period;
@ -322,7 +343,7 @@ static u64 arm_spe_event_to_pmsirr(struct perf_event *event)
arm_spe_event_sanitise_period(event);
reg |= ATTR_CFG_GET_FLD(attr, jitter) << SYS_PMSIRR_EL1_RND_SHIFT;
reg |= FIELD_PREP(PMSIRR_EL1_RND, ATTR_CFG_GET_FLD(attr, jitter));
reg |= event->hw.sample_period;
return reg;
@ -333,18 +354,21 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
struct perf_event_attr *attr = &event->attr;
u64 reg = 0;
reg |= ATTR_CFG_GET_FLD(attr, load_filter) << SYS_PMSFCR_EL1_LD_SHIFT;
reg |= ATTR_CFG_GET_FLD(attr, store_filter) << SYS_PMSFCR_EL1_ST_SHIFT;
reg |= ATTR_CFG_GET_FLD(attr, branch_filter) << SYS_PMSFCR_EL1_B_SHIFT;
reg |= FIELD_PREP(PMSFCR_EL1_LD, ATTR_CFG_GET_FLD(attr, load_filter));
reg |= FIELD_PREP(PMSFCR_EL1_ST, ATTR_CFG_GET_FLD(attr, store_filter));
reg |= FIELD_PREP(PMSFCR_EL1_B, ATTR_CFG_GET_FLD(attr, branch_filter));
if (reg)
reg |= BIT(SYS_PMSFCR_EL1_FT_SHIFT);
reg |= PMSFCR_EL1_FT;
if (ATTR_CFG_GET_FLD(attr, event_filter))
reg |= BIT(SYS_PMSFCR_EL1_FE_SHIFT);
reg |= PMSFCR_EL1_FE;
if (ATTR_CFG_GET_FLD(attr, inv_event_filter))
reg |= PMSFCR_EL1_FnE;
if (ATTR_CFG_GET_FLD(attr, min_latency))
reg |= BIT(SYS_PMSFCR_EL1_FL_SHIFT);
reg |= PMSFCR_EL1_FL;
return reg;
}
@ -355,11 +379,16 @@ static u64 arm_spe_event_to_pmsevfr(struct perf_event *event)
return ATTR_CFG_GET_FLD(attr, event_filter);
}
static u64 arm_spe_event_to_pmsnevfr(struct perf_event *event)
{
struct perf_event_attr *attr = &event->attr;
return ATTR_CFG_GET_FLD(attr, inv_event_filter);
}
static u64 arm_spe_event_to_pmslatfr(struct perf_event *event)
{
struct perf_event_attr *attr = &event->attr;
return ATTR_CFG_GET_FLD(attr, min_latency)
<< SYS_PMSLATFR_EL1_MINLAT_SHIFT;
return FIELD_PREP(PMSLATFR_EL1_MINLAT, ATTR_CFG_GET_FLD(attr, min_latency));
}
static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len)
@ -511,7 +540,7 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle,
limit = buf->snapshot ? arm_spe_pmu_next_snapshot_off(handle)
: arm_spe_pmu_next_off(handle);
if (limit)
limit |= BIT(SYS_PMBLIMITR_EL1_E_SHIFT);
limit |= PMBLIMITR_EL1_E;
limit += (u64)buf->base;
base = (u64)buf->base + PERF_IDX2OFF(handle->head, buf);
@ -570,28 +599,28 @@ arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle)
/* Service required? */
pmbsr = read_sysreg_s(SYS_PMBSR_EL1);
if (!(pmbsr & BIT(SYS_PMBSR_EL1_S_SHIFT)))
if (!FIELD_GET(PMBSR_EL1_S, pmbsr))
return SPE_PMU_BUF_FAULT_ACT_SPURIOUS;
/*
* If we've lost data, disable profiling and also set the PARTIAL
* flag to indicate that the last record is corrupted.
*/
if (pmbsr & BIT(SYS_PMBSR_EL1_DL_SHIFT))
if (FIELD_GET(PMBSR_EL1_DL, pmbsr))
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED |
PERF_AUX_FLAG_PARTIAL);
/* Report collisions to userspace so that it can up the period */
if (pmbsr & BIT(SYS_PMBSR_EL1_COLL_SHIFT))
if (FIELD_GET(PMBSR_EL1_COLL, pmbsr))
perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION);
/* We only expect buffer management events */
switch (pmbsr & (SYS_PMBSR_EL1_EC_MASK << SYS_PMBSR_EL1_EC_SHIFT)) {
case SYS_PMBSR_EL1_EC_BUF:
switch (FIELD_GET(PMBSR_EL1_EC, pmbsr)) {
case PMBSR_EL1_EC_BUF:
/* Handled below */
break;
case SYS_PMBSR_EL1_EC_FAULT_S1:
case SYS_PMBSR_EL1_EC_FAULT_S2:
case PMBSR_EL1_EC_FAULT_S1:
case PMBSR_EL1_EC_FAULT_S2:
err_str = "Unexpected buffer fault";
goto out_err;
default:
@ -600,9 +629,8 @@ arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle)
}
/* Buffer management event */
switch (pmbsr &
(SYS_PMBSR_EL1_BUF_BSC_MASK << SYS_PMBSR_EL1_BUF_BSC_SHIFT)) {
case SYS_PMBSR_EL1_BUF_BSC_FULL:
switch (FIELD_GET(PMBSR_EL1_BUF_BSC_MASK, pmbsr)) {
case PMBSR_EL1_BUF_BSC_FULL:
ret = SPE_PMU_BUF_FAULT_ACT_OK;
goto out_stop;
default:
@ -677,11 +705,13 @@ static u64 arm_spe_pmsevfr_res0(u16 pmsver)
{
switch (pmsver) {
case ID_AA64DFR0_EL1_PMSVer_IMP:
return SYS_PMSEVFR_EL1_RES0_8_2;
return PMSEVFR_EL1_RES0_IMP;
case ID_AA64DFR0_EL1_PMSVer_V1P1:
return PMSEVFR_EL1_RES0_V1P1;
case ID_AA64DFR0_EL1_PMSVer_V1P2:
/* Return the highest version we support in default */
default:
return SYS_PMSEVFR_EL1_RES0_8_3;
return PMSEVFR_EL1_RES0_V1P2;
}
}
@ -703,6 +733,9 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
return -EOPNOTSUPP;
if (arm_spe_event_to_pmsnevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
return -EOPNOTSUPP;
if (attr->exclude_idle)
return -EOPNOTSUPP;
@ -717,23 +750,26 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
return -EINVAL;
reg = arm_spe_event_to_pmsfcr(event);
if ((reg & BIT(SYS_PMSFCR_EL1_FE_SHIFT)) &&
if ((FIELD_GET(PMSFCR_EL1_FE, reg)) &&
!(spe_pmu->features & SPE_PMU_FEAT_FILT_EVT))
return -EOPNOTSUPP;
if ((reg & BIT(SYS_PMSFCR_EL1_FT_SHIFT)) &&
if ((FIELD_GET(PMSFCR_EL1_FnE, reg)) &&
!(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
return -EOPNOTSUPP;
if ((FIELD_GET(PMSFCR_EL1_FT, reg)) &&
!(spe_pmu->features & SPE_PMU_FEAT_FILT_TYP))
return -EOPNOTSUPP;
if ((reg & BIT(SYS_PMSFCR_EL1_FL_SHIFT)) &&
if ((FIELD_GET(PMSFCR_EL1_FL, reg)) &&
!(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
return -EOPNOTSUPP;
set_spe_event_has_cx(event);
reg = arm_spe_event_to_pmscr(event);
if (!perfmon_capable() &&
(reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) |
BIT(SYS_PMSCR_EL1_PCT_SHIFT))))
(reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT)))
return -EACCES;
return 0;
@ -757,6 +793,11 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags)
reg = arm_spe_event_to_pmsevfr(event);
write_sysreg_s(reg, SYS_PMSEVFR_EL1);
if (spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT) {
reg = arm_spe_event_to_pmsnevfr(event);
write_sysreg_s(reg, SYS_PMSNEVFR_EL1);
}
reg = arm_spe_event_to_pmslatfr(event);
write_sysreg_s(reg, SYS_PMSLATFR_EL1);
@ -971,14 +1012,14 @@ static void __arm_spe_pmu_dev_probe(void *info)
/* Read PMBIDR first to determine whether or not we have access */
reg = read_sysreg_s(SYS_PMBIDR_EL1);
if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) {
if (FIELD_GET(PMBIDR_EL1_P, reg)) {
dev_err(dev,
"profiling buffer owned by higher exception level\n");
return;
}
/* Minimum alignment. If it's out-of-range, then fail the probe */
fld = reg >> SYS_PMBIDR_EL1_ALIGN_SHIFT & SYS_PMBIDR_EL1_ALIGN_MASK;
fld = FIELD_GET(PMBIDR_EL1_ALIGN, reg);
spe_pmu->align = 1 << fld;
if (spe_pmu->align > SZ_2K) {
dev_err(dev, "unsupported PMBIDR.Align [%d] on CPU %d\n",
@ -988,58 +1029,61 @@ static void __arm_spe_pmu_dev_probe(void *info)
/* It's now safe to read PMSIDR and figure out what we've got */
reg = read_sysreg_s(SYS_PMSIDR_EL1);
if (reg & BIT(SYS_PMSIDR_EL1_FE_SHIFT))
if (FIELD_GET(PMSIDR_EL1_FE, reg))
spe_pmu->features |= SPE_PMU_FEAT_FILT_EVT;
if (reg & BIT(SYS_PMSIDR_EL1_FT_SHIFT))
if (FIELD_GET(PMSIDR_EL1_FnE, reg))
spe_pmu->features |= SPE_PMU_FEAT_INV_FILT_EVT;
if (FIELD_GET(PMSIDR_EL1_FT, reg))
spe_pmu->features |= SPE_PMU_FEAT_FILT_TYP;
if (reg & BIT(SYS_PMSIDR_EL1_FL_SHIFT))
if (FIELD_GET(PMSIDR_EL1_FL, reg))
spe_pmu->features |= SPE_PMU_FEAT_FILT_LAT;
if (reg & BIT(SYS_PMSIDR_EL1_ARCHINST_SHIFT))
if (FIELD_GET(PMSIDR_EL1_ARCHINST, reg))
spe_pmu->features |= SPE_PMU_FEAT_ARCH_INST;
if (reg & BIT(SYS_PMSIDR_EL1_LDS_SHIFT))
if (FIELD_GET(PMSIDR_EL1_LDS, reg))
spe_pmu->features |= SPE_PMU_FEAT_LDS;
if (reg & BIT(SYS_PMSIDR_EL1_ERND_SHIFT))
if (FIELD_GET(PMSIDR_EL1_ERND, reg))
spe_pmu->features |= SPE_PMU_FEAT_ERND;
/* This field has a spaced out encoding, so just use a look-up */
fld = reg >> SYS_PMSIDR_EL1_INTERVAL_SHIFT & SYS_PMSIDR_EL1_INTERVAL_MASK;
fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg);
switch (fld) {
case 0:
case PMSIDR_EL1_INTERVAL_256:
spe_pmu->min_period = 256;
break;
case 2:
case PMSIDR_EL1_INTERVAL_512:
spe_pmu->min_period = 512;
break;
case 3:
case PMSIDR_EL1_INTERVAL_768:
spe_pmu->min_period = 768;
break;
case 4:
case PMSIDR_EL1_INTERVAL_1024:
spe_pmu->min_period = 1024;
break;
case 5:
case PMSIDR_EL1_INTERVAL_1536:
spe_pmu->min_period = 1536;
break;
case 6:
case PMSIDR_EL1_INTERVAL_2048:
spe_pmu->min_period = 2048;
break;
case 7:
case PMSIDR_EL1_INTERVAL_3072:
spe_pmu->min_period = 3072;
break;
default:
dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n",
fld);
fallthrough;
case 8:
case PMSIDR_EL1_INTERVAL_4096:
spe_pmu->min_period = 4096;
}
/* Maximum record size. If it's out-of-range, then fail the probe */
fld = reg >> SYS_PMSIDR_EL1_MAXSIZE_SHIFT & SYS_PMSIDR_EL1_MAXSIZE_MASK;
fld = FIELD_GET(PMSIDR_EL1_MAXSIZE, reg);
spe_pmu->max_record_sz = 1 << fld;
if (spe_pmu->max_record_sz > SZ_2K || spe_pmu->max_record_sz < 16) {
dev_err(dev, "unsupported PMSIDR_EL1.MaxSize [%d] on CPU %d\n",
@ -1047,22 +1091,22 @@ static void __arm_spe_pmu_dev_probe(void *info)
return;
}
fld = reg >> SYS_PMSIDR_EL1_COUNTSIZE_SHIFT & SYS_PMSIDR_EL1_COUNTSIZE_MASK;
fld = FIELD_GET(PMSIDR_EL1_COUNTSIZE, reg);
switch (fld) {
default:
dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n",
fld);
fallthrough;
case 2:
case PMSIDR_EL1_COUNTSIZE_12_BIT_SAT:
spe_pmu->counter_sz = 12;
break;
case 3:
case PMSIDR_EL1_COUNTSIZE_16_BIT_SAT:
spe_pmu->counter_sz = 16;
}
dev_info(dev,
"probed for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n",
cpumask_pr_args(&spe_pmu->supported_cpus),
"probed SPEv1.%d for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n",
spe_pmu->pmsver - 1, cpumask_pr_args(&spe_pmu->supported_cpus),
spe_pmu->max_record_sz, spe_pmu->align, spe_pmu->features);
spe_pmu->features |= SPE_PMU_FEAT_DEV_PROBED;

3
drivers/perf/fsl_imx8_ddr_perf.c
View File

@ -97,7 +97,6 @@ struct ddr_pmu {
struct hlist_node node;
struct device *dev;
struct perf_event *events[NUM_COUNTERS];
int active_events;
enum cpuhp_state cpuhp_state;
const struct fsl_ddr_devtype_data *devtype_data;
int irq;
@ -530,7 +529,6 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
}
pmu->events[counter] = event;
pmu->active_events++;
hwc->idx = counter;
hwc->state |= PERF_HES_STOPPED;
@ -562,7 +560,6 @@ static void ddr_perf_event_del(struct perf_event *event, int flags)
ddr_perf_event_stop(event, PERF_EF_UPDATE);
ddr_perf_free_counter(pmu, counter);
pmu->active_events--;
hwc->idx = -1;
}

16
drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
View File

@ -316,21 +316,7 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev)
if (!name)
return -ENOMEM;
cpa_pmu->pmu = (struct pmu) {
.name = name,
.module = THIS_MODULE,
.task_ctx_nr = perf_invalid_context,
.event_init = hisi_uncore_pmu_event_init,
.pmu_enable = hisi_uncore_pmu_enable,
.pmu_disable = hisi_uncore_pmu_disable,
.add = hisi_uncore_pmu_add,
.del = hisi_uncore_pmu_del,
.start = hisi_uncore_pmu_start,
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
.attr_groups = cpa_pmu->pmu_events.attr_groups,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
hisi_pmu_init(cpa_pmu, name, THIS_MODULE);
/* Power Management should be disabled before using CPA PMU. */
hisi_cpa_pmu_disable_pm(cpa_pmu);

2
drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
View File

@ -516,7 +516,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
"hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id,
ddrc_pmu->index_id);
hisi_pmu_init(&ddrc_pmu->pmu, name, ddrc_pmu->pmu_events.attr_groups, THIS_MODULE);
hisi_pmu_init(ddrc_pmu, name, THIS_MODULE);
ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);
if (ret) {

2
drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
View File

@ -519,7 +519,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u",
hha_pmu->sccl_id, hha_pmu->index_id);
hisi_pmu_init(&hha_pmu->pmu, name, hha_pmu->pmu_events.attr_groups, THIS_MODULE);
hisi_pmu_init(hha_pmu, name, THIS_MODULE);
ret = perf_pmu_register(&hha_pmu->pmu, name, -1);
if (ret) {

2
drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
View File

@ -557,7 +557,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
*/
name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
l3c_pmu->sccl_id, l3c_pmu->ccl_id);
hisi_pmu_init(&l3c_pmu->pmu, name, l3c_pmu->pmu_events.attr_groups, THIS_MODULE);
hisi_pmu_init(l3c_pmu, name, THIS_MODULE);
ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);
if (ret) {

2
drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
View File

@ -412,7 +412,7 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev)
return ret;
}
hisi_pmu_init(&pa_pmu->pmu, name, pa_pmu->pmu_events.attr_groups, THIS_MODULE);
hisi_pmu_init(pa_pmu, name, THIS_MODULE);
ret = perf_pmu_register(&pa_pmu->pmu, name, -1);
if (ret) {
dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);

9
drivers/perf/hisilicon/hisi_uncore_pmu.c
View File

@ -531,9 +531,11 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
}
EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu);
void hisi_pmu_init(struct pmu *pmu, const char *name,
const struct attribute_group **attr_groups, struct module *module)
void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name,
struct module *module)
{
struct pmu *pmu = &hisi_pmu->pmu;
pmu->name = name;
pmu->module = module;
pmu->task_ctx_nr = perf_invalid_context;
@ -545,7 +547,8 @@ void hisi_pmu_init(struct pmu *pmu, const char *name,
pmu->start = hisi_uncore_pmu_start;
pmu->stop = hisi_uncore_pmu_stop;
pmu->read = hisi_uncore_pmu_read;
pmu->attr_groups = attr_groups;
pmu->attr_groups = hisi_pmu->pmu_events.attr_groups;
pmu->capabilities = PERF_PMU_CAP_NO_EXCLUDE;
}
EXPORT_SYMBOL_GPL(hisi_pmu_init);

4
drivers/perf/hisilicon/hisi_uncore_pmu.h
View File

@ -121,6 +121,6 @@ ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev,
int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
struct platform_device *pdev);
void hisi_pmu_init(struct pmu *pmu, const char *name,
const struct attribute_group **attr_groups, struct module *module);
void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name,
struct module *module);
#endif /* __HISI_UNCORE_PMU_H__ */

2
drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
View File

@ -445,7 +445,7 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev)
return ret;
}
hisi_pmu_init(&sllc_pmu->pmu, name, sllc_pmu->pmu_events.attr_groups, THIS_MODULE);
hisi_pmu_init(sllc_pmu, name, THIS_MODULE);
ret = perf_pmu_register(&sllc_pmu->pmu, name, -1);
if (ret) {

10
drivers/perf/marvell_cn10k_ddr_pmu.c
View File

@ -12,6 +12,7 @@
#include <linux/of_device.h>
#include <linux/perf_event.h>
#include <linux/hrtimer.h>
#include <linux/acpi.h>
/* Performance Counters Operating Mode Control Registers */
#define DDRC_PERF_CNT_OP_MODE_CTRL 0x8020
@ -717,10 +718,19 @@ static const struct of_device_id cn10k_ddr_pmu_of_match[] = {
MODULE_DEVICE_TABLE(of, cn10k_ddr_pmu_of_match);
#endif
#ifdef CONFIG_ACPI
static const struct acpi_device_id cn10k_ddr_pmu_acpi_match[] = {
{"MRVL000A", 0},
{},
};
MODULE_DEVICE_TABLE(acpi, cn10k_ddr_pmu_acpi_match);
#endif
static struct platform_driver cn10k_ddr_pmu_driver = {
.driver = {
.name = "cn10k-ddr-pmu",
.of_match_table = of_match_ptr(cn10k_ddr_pmu_of_match),
.acpi_match_table = ACPI_PTR(cn10k_ddr_pmu_acpi_match),
.suppress_bind_attrs = true,
},
.probe = cn10k_ddr_perf_probe,

22
drivers/perf/marvell_cn10k_tad_pmu.c
View File

@ -13,6 +13,7 @@
#include <linux/cpuhotplug.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <linux/acpi.h>
#define TAD_PFC_OFFSET 0x800
#define TAD_PFC(counter) (TAD_PFC_OFFSET | (counter << 3))
@ -254,7 +255,7 @@ static const struct attribute_group *tad_pmu_attr_groups[] = {
static int tad_pmu_probe(struct platform_device *pdev)
{
struct device_node *node = pdev->dev.of_node;
struct device *dev = &pdev->dev;
struct tad_region *regions;
struct tad_pmu *tad_pmu;
struct resource *res;
@ -276,21 +277,21 @@ static int tad_pmu_probe(struct platform_device *pdev)
return -ENODEV;
}
ret = of_property_read_u32(node, "marvell,tad-page-size",
&tad_page_size);
ret = device_property_read_u32(dev, "marvell,tad-page-size",
&tad_page_size);
if (ret) {
dev_err(&pdev->dev, "Can't find tad-page-size property\n");
return ret;
}
ret = of_property_read_u32(node, "marvell,tad-pmu-page-size",
&tad_pmu_page_size);
ret = device_property_read_u32(dev, "marvell,tad-pmu-page-size",
&tad_pmu_page_size);
if (ret) {
dev_err(&pdev->dev, "Can't find tad-pmu-page-size property\n");
return ret;
}
ret = of_property_read_u32(node, "marvell,tad-cnt", &tad_cnt);
ret = device_property_read_u32(dev, "marvell,tad-cnt", &tad_cnt);
if (ret) {
dev_err(&pdev->dev, "Can't find tad-cnt property\n");
return ret;
@ -369,10 +370,19 @@ static const struct of_device_id tad_pmu_of_match[] = {
};
#endif
#ifdef CONFIG_ACPI
static const struct acpi_device_id tad_pmu_acpi_match[] = {
{"MRVL000B", 0},
{},
};
MODULE_DEVICE_TABLE(acpi, tad_pmu_acpi_match);
#endif
static struct platform_driver tad_pmu_driver = {
.driver = {
.name = "cn10k_tad_pmu",
.of_match_table = of_match_ptr(tad_pmu_of_match),
.acpi_match_table = ACPI_PTR(tad_pmu_acpi_match),
.suppress_bind_attrs = true,
},
.probe = tad_pmu_probe,

6
include/linux/compiler_attributes.h
View File

@ -75,12 +75,6 @@
# define __assume_aligned(a, ...)
#endif
/*
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute
*/
#define __cold __attribute__((__cold__))
/*
* Note the long name.
*

27
include/linux/compiler_types.h
View File

@ -79,6 +79,33 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
/* Attributes */
#include <linux/compiler_attributes.h>
#if CONFIG_FUNCTION_ALIGNMENT > 0
#define __function_aligned __aligned(CONFIG_FUNCTION_ALIGNMENT)
#else
#define __function_aligned
#endif
/*
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute
*
* When -falign-functions=N is in use, we must avoid the cold attribute as
* contemporary versions of GCC drop the alignment for cold functions. Worse,
* GCC can implicitly mark callees of cold functions as cold themselves, so
* it's not sufficient to add __function_aligned here as that will not ensure
* that callees are correctly aligned.
*
* See:
*
* https://lore.kernel.org/lkml/Y77%2FqVgvaJidFpYt@FVFF77S0Q05N
* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c9
*/
#if !defined(CONFIG_CC_IS_GCC) || (CONFIG_FUNCTION_ALIGNMENT == 0)
#define __cold __attribute__((__cold__))
#else
#define __cold
#endif
/* Builtins */
/*

18
include/linux/ftrace.h
View File

@ -39,6 +39,7 @@ static inline void ftrace_boot_snapshot(void) { }
struct ftrace_ops;
struct ftrace_regs;
struct dyn_ftrace;
#ifdef CONFIG_FUNCTION_TRACER
/*
@ -57,6 +58,9 @@ void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs);
#endif
extern const struct ftrace_ops ftrace_nop_ops;
extern const struct ftrace_ops ftrace_list_ops;
struct ftrace_ops *ftrace_find_unique_ops(struct dyn_ftrace *rec);
#endif /* CONFIG_FUNCTION_TRACER */
/* Main tracing buffer and events set up */
@ -391,8 +395,6 @@ struct ftrace_func_entry {
unsigned long direct; /* for direct lookup only */
};
struct dyn_ftrace;
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
extern int ftrace_direct_func_count;
int register_ftrace_direct(unsigned long ip, unsigned long addr);
@ -563,6 +565,8 @@ bool is_ftrace_trampoline(unsigned long addr);
* IPMODIFY - the record allows for the IP address to be changed.
* DISABLED - the record is not ready to be touched yet
* DIRECT - there is a direct function to call
* CALL_OPS - the record can use callsite-specific ops
* CALL_OPS_EN - the function is set up to use callsite-specific ops
*
* When a new ftrace_ops is registered and wants a function to save
* pt_regs, the rec->flags REGS is set. When the function has been
@ -580,9 +584,11 @@ enum {
FTRACE_FL_DISABLED = (1UL << 25),
FTRACE_FL_DIRECT = (1UL << 24),
FTRACE_FL_DIRECT_EN = (1UL << 23),
FTRACE_FL_CALL_OPS = (1UL << 22),
FTRACE_FL_CALL_OPS_EN = (1UL << 21),
};
#define FTRACE_REF_MAX_SHIFT 23
#define FTRACE_REF_MAX_SHIFT 21
#define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1)
#define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX)
@ -820,7 +826,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
*/
extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
#if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \
defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)
/**
* ftrace_modify_call - convert from one addr to another (no nop)
* @rec: the call site record (e.g. mcount/fentry)
@ -833,6 +840,9 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
* When using call ops, this is called when the associated ops change, even
* when (addr == old_addr).
*
* The code segment at @rec->ip should be a caller to @old_addr
*
* Return must be:

1
include/uapi/linux/elf.h
View File

@ -434,6 +434,7 @@ typedef struct elf64_shdr {
#define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */
#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */
#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */
#define NT_ARM_ZT 0x40d /* ARM SME ZT registers */
#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */
#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */
#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */

3
include/uapi/linux/perf_event.h
View File

@ -374,6 +374,7 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */
#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */
#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */
#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */
/*
* Hardware event_id to monitor via a performance monitoring event:
@ -515,6 +516,8 @@ struct perf_event_attr {
* truncated accordingly on 32 bit architectures.
*/
__u64 sig_data;
__u64 config3; /* extension of config2 */
};
/*

9
kernel/exit.c
View File

@ -1905,7 +1905,14 @@ bool thread_group_exited(struct pid *pid)
}
EXPORT_SYMBOL(thread_group_exited);
__weak void abort(void)
/*
* This needs to be __function_aligned as GCC implicitly makes any
* implementation of abort() cold and drops alignment specified by
* -falign-functions=N.
*
* See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11
*/
__weak __function_aligned void abort(void)
{
BUG();

7
kernel/trace/Kconfig
View File

@ -42,6 +42,9 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS
config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
bool
config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
bool
config HAVE_DYNAMIC_FTRACE_WITH_ARGS
bool
help
@ -257,6 +260,10 @@ config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
depends on DYNAMIC_FTRACE_WITH_REGS
depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
config DYNAMIC_FTRACE_WITH_CALL_OPS
def_bool y
depends on HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
config DYNAMIC_FTRACE_WITH_ARGS
def_bool y
depends on DYNAMIC_FTRACE

109
kernel/trace/ftrace.c
View File

@ -125,6 +125,33 @@ struct ftrace_ops global_ops;
void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
/*
* Stub used to invoke the list ops without requiring a separate trampoline.
*/
const struct ftrace_ops ftrace_list_ops = {
.func = ftrace_ops_list_func,
.flags = FTRACE_OPS_FL_STUB,
};
static void ftrace_ops_nop_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op,
struct ftrace_regs *fregs)
{
/* do nothing */
}
/*
* Stub used when a call site is disabled. May be called transiently by threads
* which have made it into ftrace_caller but haven't yet recovered the ops at
* the point the call site is disabled.
*/
const struct ftrace_ops ftrace_nop_ops = {
.func = ftrace_ops_nop_func,
.flags = FTRACE_OPS_FL_STUB,
};
#endif
static inline void ftrace_ops_init(struct ftrace_ops *ops)
{
#ifdef CONFIG_DYNAMIC_FTRACE
@ -1819,6 +1846,18 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
* if rec count is zero.
*/
}
/*
* If the rec has a single associated ops, and ops->func can be
* called directly, allow the call site to call via the ops.
*/
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) &&
ftrace_rec_count(rec) == 1 &&
ftrace_ops_get_func(ops) == ops->func)
rec->flags |= FTRACE_FL_CALL_OPS;
else
rec->flags &= ~FTRACE_FL_CALL_OPS;
count++;
/* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */
@ -2113,8 +2152,9 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
struct ftrace_ops *ops = NULL;
pr_info("ftrace record flags: %lx\n", rec->flags);
pr_cont(" (%ld)%s", ftrace_rec_count(rec),
rec->flags & FTRACE_FL_REGS ? " R" : " ");
pr_cont(" (%ld)%s%s", ftrace_rec_count(rec),
rec->flags & FTRACE_FL_REGS ? " R" : " ",
rec->flags & FTRACE_FL_CALL_OPS ? " O" : " ");
if (rec->flags & FTRACE_FL_TRAMP_EN) {
ops = ftrace_find_tramp_ops_any(rec);
if (ops) {
@ -2182,6 +2222,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
* want the direct enabled (it will be done via the
* direct helper). But if DIRECT_EN is set, and
* the count is not one, we need to clear it.
*
*/
if (ftrace_rec_count(rec) == 1) {
if (!(rec->flags & FTRACE_FL_DIRECT) !=
@ -2190,6 +2231,19 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
} else if (rec->flags & FTRACE_FL_DIRECT_EN) {
flag |= FTRACE_FL_DIRECT;
}
/*
* Ops calls are special, as count matters.
* As with direct calls, they must only be enabled when count
* is one, otherwise they'll be handled via the list ops.
*/
if (ftrace_rec_count(rec) == 1) {
if (!(rec->flags & FTRACE_FL_CALL_OPS) !=
!(rec->flags & FTRACE_FL_CALL_OPS_EN))
flag |= FTRACE_FL_CALL_OPS;
} else if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
flag |= FTRACE_FL_CALL_OPS;
}
}
/* If the state of this record hasn't changed, then do nothing */
@ -2234,6 +2288,21 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
rec->flags &= ~FTRACE_FL_DIRECT_EN;
}
}
if (flag & FTRACE_FL_CALL_OPS) {
if (ftrace_rec_count(rec) == 1) {
if (rec->flags & FTRACE_FL_CALL_OPS)
rec->flags |= FTRACE_FL_CALL_OPS_EN;
else
rec->flags &= ~FTRACE_FL_CALL_OPS_EN;
} else {
/*
* Can only call directly if there's
* only one set of associated ops.
*/
rec->flags &= ~FTRACE_FL_CALL_OPS_EN;
}
}
}
/*
@ -2263,7 +2332,8 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
* and REGS states. The _EN flags must be disabled though.
*/
rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN |
FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN);
FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN |
FTRACE_FL_CALL_OPS_EN);
}
ftrace_bug_type = FTRACE_BUG_NOP;
@ -2436,6 +2506,25 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec)
return NULL;
}
struct ftrace_ops *
ftrace_find_unique_ops(struct dyn_ftrace *rec)
{
struct ftrace_ops *op, *found = NULL;
unsigned long ip = rec->ip;
do_for_each_ftrace_op(op, ftrace_ops_list) {
if (hash_contains_ip(ip, op->func_hash)) {
if (found)
return NULL;
found = op;
}
} while_for_each_ftrace_op(op);
return found;
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
/* Protected by rcu_tasks for reading, and direct_mutex for writing */
static struct ftrace_hash *direct_functions = EMPTY_HASH;
@ -3785,11 +3874,12 @@ static int t_show(struct seq_file *m, void *v)
if (iter->flags & FTRACE_ITER_ENABLED) {
struct ftrace_ops *ops;
seq_printf(m, " (%ld)%s%s%s",
seq_printf(m, " (%ld)%s%s%s%s",
ftrace_rec_count(rec),
rec->flags & FTRACE_FL_REGS ? " R" : " ",
rec->flags & FTRACE_FL_IPMODIFY ? " I" : " ",
rec->flags & FTRACE_FL_DIRECT ? " D" : " ");
rec->flags & FTRACE_FL_DIRECT ? " D" : " ",
rec->flags & FTRACE_FL_CALL_OPS ? " O" : " ");
if (rec->flags & FTRACE_FL_TRAMP_EN) {
ops = ftrace_find_tramp_ops_any(rec);
if (ops) {
@ -3805,6 +3895,15 @@ static int t_show(struct seq_file *m, void *v)
} else {
add_trampoline_func(m, NULL, rec);
}
if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
ops = ftrace_find_unique_ops(rec);
if (ops) {
seq_printf(m, "\tops: %pS (%pS)",
ops, ops->func);
} else {
seq_puts(m, "\tops: ERROR!");
}
}
if (rec->flags & FTRACE_FL_DIRECT) {
unsigned long direct;

115
tools/testing/selftests/arm64/abi/hwcap.c
View File

@ -50,6 +50,78 @@ static void sme_sigill(void)
asm volatile(".inst 0x04bf5800" : : : "x0");
}
static void sme2_sigill(void)
{
/* SMSTART ZA */
asm volatile("msr S0_3_C4_C5_3, xzr" : : : );
/* ZERO ZT0 */
asm volatile(".inst 0xc0480001" : : : );
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
static void sme2p1_sigill(void)
{
/* SMSTART SM */
asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
/* BFCLAMP { Z0.H - Z1.H }, Z0.H, Z0.H */
asm volatile(".inst 0xc120C000" : : : );
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
static void smei16i32_sigill(void)
{
/* SMSTART */
asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
/* SMOPA ZA0.S, P0/M, P0/M, Z0.B, Z0.B */
asm volatile(".inst 0xa0800000" : : : );
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
static void smebi32i32_sigill(void)
{
/* SMSTART */
asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
/* BMOPA ZA0.S, P0/M, P0/M, Z0.B, Z0.B */
asm volatile(".inst 0x80800008" : : : );
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
static void smeb16b16_sigill(void)
{
/* SMSTART */
asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
/* BFADD ZA.H[W0, 0], {Z0.H-Z1.H} */
asm volatile(".inst 0xC1E41C00" : : : );
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
static void smef16f16_sigill(void)
{
/* SMSTART */
asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
/* FADD ZA.H[W0, 0], { Z0.H-Z1.H } */
asm volatile(".inst 0xc1a41C00" : : : );
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
static void sve_sigill(void)
{
/* RDVL x0, #0 */
@ -158,6 +230,49 @@ static const struct hwcap_data {
.sigill_fn = sme_sigill,
.sigill_reliable = true,
},
{
.name = "SME2",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME2,
.cpuinfo = "sme2",
.sigill_fn = sme2_sigill,
.sigill_reliable = true,
},
{
.name = "SME 2.1",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME2P1,
.cpuinfo = "sme2p1",
.sigill_fn = sme2p1_sigill,
},
{
.name = "SME I16I32",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME_I16I32,
.cpuinfo = "smei16i32",
.sigill_fn = smei16i32_sigill,
},
{
.name = "SME BI32I32",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME_BI32I32,
.cpuinfo = "smebi32i32",
.sigill_fn = smebi32i32_sigill,
},
{
.name = "SME B16B16",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME_B16B16,
.cpuinfo = "smeb16b16",
.sigill_fn = smeb16b16_sigill,
},
{
.name = "SME F16F16",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME_F16F16,
.cpuinfo = "smef16f16",
.sigill_fn = smef16f16_sigill,
},
{
.name = "SVE",
.at_hwcap = AT_HWCAP,

57
tools/testing/selftests/arm64/abi/syscall-abi-asm.S
View File

@ -23,6 +23,9 @@
.arch_extension sve
#define ID_AA64SMFR0_EL1_SMEver_SHIFT 56
#define ID_AA64SMFR0_EL1_SMEver_WIDTH 4
/*
* LDR (vector to ZA array):
* LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
@ -45,6 +48,26 @@
| ((\offset) & 7)
.endm
/*
* LDR (ZT0)
*
* LDR ZT0, nx
*/
.macro _ldr_zt nx
.inst 0xe11f8000 \
| (((\nx) & 0x1f) << 5)
.endm
/*
* STR (ZT0)
*
* STR ZT0, nx
*/
.macro _str_zt nx
.inst 0xe13f8000 \
| (((\nx) & 0x1f) << 5)
.endm
.globl do_syscall
do_syscall:
// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
@ -64,7 +87,7 @@ do_syscall:
msr S3_3_C4_C2_2, x2
1:
// Load ZA if it's enabled - uses x12 as scratch due to SME LDR
// Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR
tbz x2, #SVCR_ZA_SHIFT, 1f
mov w12, #0
ldr x2, =za_in
@ -73,6 +96,15 @@ do_syscall:
add x12, x12, #1
cmp x1, x12
bne 2b
// ZT0
mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1
ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
#ID_AA64SMFR0_EL1_SMEver_WIDTH
cbz x2, 1f
adrp x2, zt_in
add x2, x2, :lo12:zt_in
_ldr_zt 2
1:
// Load GPRs x8-x28, and save our SP/FP for later comparison
@ -92,8 +124,11 @@ do_syscall:
str x29, [x2], #8 // FP
str x30, [x2], #8 // LR
// Load FPRs if we're not doing SVE
// Load FPRs if we're not doing neither SVE nor streaming SVE
cbnz x0, 1f
ldr x2, =svcr_in
tbnz x2, #SVCR_SM_SHIFT, 1f
ldr x2, =fpr_in
ldp q0, q1, [x2]
ldp q2, q3, [x2, #16 * 2]
@ -111,10 +146,11 @@ do_syscall:
ldp q26, q27, [x2, #16 * 26]
ldp q28, q29, [x2, #16 * 28]
ldp q30, q31, [x2, #16 * 30]
b 2f
1:
// Load the SVE registers if we're doing SVE/SME
cbz x0, 1f
ldr x2, =z_in
ldr z0, [x2, #0, MUL VL]
@ -155,9 +191,9 @@ do_syscall:
ldr x2, =ffr_in
ldr p0, [x2]
ldr x2, [x2, #0]
cbz x2, 2f
cbz x2, 1f
wrffr p0.b
2:
1:
ldr x2, =p_in
ldr p0, [x2, #0, MUL VL]
@ -176,7 +212,7 @@ do_syscall:
ldr p13, [x2, #13, MUL VL]
ldr p14, [x2, #14, MUL VL]
ldr p15, [x2, #15, MUL VL]
1:
2:
// Do the syscall
svc #0
@ -235,6 +271,15 @@ do_syscall:
add x12, x12, #1
cmp x1, x12
bne 2b
// ZT0
mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1
ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
#ID_AA64SMFR0_EL1_SMEver_WIDTH
cbz x2, 1f
adrp x2, zt_out
add x2, x2, :lo12:zt_out
_str_zt 2
1:
// Save the SVE state if we have some

179
tools/testing/selftests/arm64/abi/syscall-abi.c
View File

@ -20,10 +20,13 @@
#include "syscall-abi.h"
#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
static int default_sme_vl;
static int sve_vl_count;
static unsigned int sve_vls[SVE_VQ_MAX];
static int sme_vl_count;
static unsigned int sme_vls[SVE_VQ_MAX];
extern void do_syscall(int sve_vl, int sme_vl);
static void fill_random(void *buf, size_t size)
@ -83,6 +86,7 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t s
#define NUM_FPR 32
uint64_t fpr_in[NUM_FPR * 2];
uint64_t fpr_out[NUM_FPR * 2];
uint64_t fpr_zero[NUM_FPR * 2];
static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
uint64_t svcr)
@ -97,7 +101,7 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
int errors = 0;
int i;
if (!sve_vl) {
if (!sve_vl && !(svcr & SVCR_SM_MASK)) {
for (i = 0; i < ARRAY_SIZE(fpr_in); i++) {
if (fpr_in[i] != fpr_out[i]) {
ksft_print_msg("%s Q%d/%d mismatch %llx != %llx\n",
@ -109,6 +113,18 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
}
}
/*
* In streaming mode the whole register set should be cleared
* by the transition out of streaming mode.
*/
if (svcr & SVCR_SM_MASK) {
if (memcmp(fpr_zero, fpr_out, sizeof(fpr_out)) != 0) {
ksft_print_msg("%s FPSIMD registers non-zero exiting SM\n",
cfg->name);
errors++;
}
}
return errors;
}
@ -284,8 +300,8 @@ static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
return errors;
}
uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
uint8_t za_in[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
uint8_t za_out[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
uint64_t svcr)
@ -311,6 +327,35 @@ static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
return errors;
}
uint8_t zt_in[ZT_SIG_REG_BYTES] __attribute__((aligned(16)));
uint8_t zt_out[ZT_SIG_REG_BYTES] __attribute__((aligned(16)));
static void setup_zt(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
uint64_t svcr)
{
fill_random(zt_in, sizeof(zt_in));
memset(zt_out, 0, sizeof(zt_out));
}
static int check_zt(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
uint64_t svcr)
{
int errors = 0;
if (!(getauxval(AT_HWCAP2) & HWCAP2_SME2))
return 0;
if (!(svcr & SVCR_ZA_MASK))
return 0;
if (memcmp(zt_in, zt_out, sizeof(zt_in)) != 0) {
ksft_print_msg("SME VL %d ZT does not match\n", sme_vl);
errors++;
}
return errors;
}
typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
uint64_t svcr);
typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
@ -334,6 +379,7 @@ static struct {
{ setup_ffr, check_ffr },
{ setup_svcr, check_svcr },
{ setup_za, check_za },
{ setup_zt, check_zt },
};
static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
@ -355,73 +401,78 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
static void test_one_syscall(struct syscall_cfg *cfg)
{
int sve_vq, sve_vl;
int sme_vq, sme_vl;
int sve, sme;
int ret;
/* FPSIMD only case */
ksft_test_result(do_test(cfg, 0, default_sme_vl, 0),
"%s FPSIMD\n", cfg->name);
if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
return;
for (sve_vq = SVE_VQ_MAX; sve_vq > 0; --sve_vq) {
sve_vl = prctl(PR_SVE_SET_VL, sve_vq * 16);
if (sve_vl == -1)
for (sve = 0; sve < sve_vl_count; sve++) {
ret = prctl(PR_SVE_SET_VL, sve_vls[sve]);
if (ret == -1)
ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
strerror(errno), errno);
sve_vl &= PR_SVE_VL_LEN_MASK;
ksft_test_result(do_test(cfg, sve_vls[sve], default_sme_vl, 0),
"%s SVE VL %d\n", cfg->name, sve_vls[sve]);
if (sve_vq != sve_vq_from_vl(sve_vl))
sve_vq = sve_vq_from_vl(sve_vl);
ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0),
"%s SVE VL %d\n", cfg->name, sve_vl);
if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
continue;
for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) {
sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16);
if (sme_vl == -1)
for (sme = 0; sme < sme_vl_count; sme++) {
ret = prctl(PR_SME_SET_VL, sme_vls[sme]);
if (ret == -1)
ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
strerror(errno), errno);
sme_vl &= PR_SME_VL_LEN_MASK;
if (sme_vq != sve_vq_from_vl(sme_vl))
sme_vq = sve_vq_from_vl(sme_vl);
ksft_test_result(do_test(cfg, sve_vl, sme_vl,
ksft_test_result(do_test(cfg, sve_vls[sve],
sme_vls[sme],
SVCR_ZA_MASK | SVCR_SM_MASK),
"%s SVE VL %d/SME VL %d SM+ZA\n",
cfg->name, sve_vl, sme_vl);
ksft_test_result(do_test(cfg, sve_vl, sme_vl,
SVCR_SM_MASK),
cfg->name, sve_vls[sve],
sme_vls[sme]);
ksft_test_result(do_test(cfg, sve_vls[sve],
sme_vls[sme], SVCR_SM_MASK),
"%s SVE VL %d/SME VL %d SM\n",
cfg->name, sve_vl, sme_vl);
ksft_test_result(do_test(cfg, sve_vl, sme_vl,
SVCR_ZA_MASK),
cfg->name, sve_vls[sve],
sme_vls[sme]);
ksft_test_result(do_test(cfg, sve_vls[sve],
sme_vls[sme], SVCR_ZA_MASK),
"%s SVE VL %d/SME VL %d ZA\n",
cfg->name, sve_vl, sme_vl);
cfg->name, sve_vls[sve],
sme_vls[sme]);
}
}
for (sme = 0; sme < sme_vl_count; sme++) {
ret = prctl(PR_SME_SET_VL, sme_vls[sme]);
if (ret == -1)
ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
strerror(errno), errno);
ksft_test_result(do_test(cfg, 0, sme_vls[sme],
SVCR_ZA_MASK | SVCR_SM_MASK),
"%s SME VL %d SM+ZA\n",
cfg->name, sme_vls[sme]);
ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_SM_MASK),
"%s SME VL %d SM\n",
cfg->name, sme_vls[sme]);
ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_ZA_MASK),
"%s SME VL %d ZA\n",
cfg->name, sme_vls[sme]);
}
}
int sve_count_vls(void)
void sve_count_vls(void)
{
unsigned int vq;
int vl_count = 0;
int vl;
if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
return 0;
return;
/*
* Enumerate up to SVE_VQ_MAX vector lengths
*/
for (vq = SVE_VQ_MAX; vq > 0; --vq) {
for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
vl = prctl(PR_SVE_SET_VL, vq * 16);
if (vl == -1)
ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
@ -432,28 +483,22 @@ int sve_count_vls(void)
if (vq != sve_vq_from_vl(vl))
vq = sve_vq_from_vl(vl);
vl_count++;
sve_vls[sve_vl_count++] = vl;
}
return vl_count;
}
int sme_count_vls(void)
void sme_count_vls(void)
{
unsigned int vq;
int vl_count = 0;
int vl;
if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
return 0;
/* Ensure we configure a SME VL, used to flag if SVCR is set */
default_sme_vl = 16;
return;
/*
* Enumerate up to SVE_VQ_MAX vector lengths
*/
for (vq = SVE_VQ_MAX; vq > 0; --vq) {
for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
vl = prctl(PR_SME_SET_VL, vq * 16);
if (vl == -1)
ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
@ -461,31 +506,47 @@ int sme_count_vls(void)
vl &= PR_SME_VL_LEN_MASK;
/* Found lowest VL */
if (sve_vq_from_vl(vl) > vq)
break;
if (vq != sve_vq_from_vl(vl))
vq = sve_vq_from_vl(vl);
vl_count++;
sme_vls[sme_vl_count++] = vl;
}
return vl_count;
/* Ensure we configure a SME VL, used to flag if SVCR is set */
default_sme_vl = sme_vls[0];
}
int main(void)
{
int i;
int tests = 1; /* FPSIMD */
int sme_ver;
srandom(getpid());
ksft_print_header();
tests += sve_count_vls();
tests += (sve_count_vls() * sme_count_vls()) * 3;
sve_count_vls();
sme_count_vls();
tests += sve_vl_count;
tests += sme_vl_count * 3;
tests += (sve_vl_count * sme_vl_count) * 3;
ksft_set_plan(ARRAY_SIZE(syscalls) * tests);
if (getauxval(AT_HWCAP2) & HWCAP2_SME2)
sme_ver = 2;
else
sme_ver = 1;
if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
ksft_print_msg("SME with FA64\n");
ksft_print_msg("SME%d with FA64\n", sme_ver);
else if (getauxval(AT_HWCAP2) & HWCAP2_SME)
ksft_print_msg("SME without FA64\n");
ksft_print_msg("SME%d without FA64\n", sme_ver);
for (i = 0; i < ARRAY_SIZE(syscalls); i++)
test_one_syscall(&syscalls[i]);

25
tools/testing/selftests/arm64/bti/test.c
View File

@ -6,6 +6,7 @@
#include "system.h"
#include <stdbool.h>
#include <stddef.h>
#include <linux/errno.h>
#include <linux/auxvec.h>
@ -101,7 +102,8 @@ static void handler(int n, siginfo_t *si __always_unused,
uc->uc_mcontext.pstate &= ~PSR_BTYPE_MASK;
}
static int skip_all;
/* Does the system have BTI? */
static bool have_bti;
static void __do_test(void (*trampoline)(void (*)(void)),
void (*fn)(void),
@ -109,19 +111,11 @@ static void __do_test(void (*trampoline)(void (*)(void)),
const char *name,
int expect_sigill)
{
if (skip_all) {
test_skipped++;
putstr("ok ");
putnum(test_num);
putstr(" ");
puttestname(name, trampoline_name);
putstr(" # SKIP\n");
return;
}
/* Branch Target exceptions should only happen in BTI binaries: */
if (!BTI)
/*
* Branch Target exceptions should only happen for BTI
* binaries running on a system with BTI:
*/
if (!BTI || !have_bti)
expect_sigill = 0;
sigill_expected = expect_sigill;
@ -199,9 +193,10 @@ void start(int *argcp)
putstr("# HWCAP2_BTI present\n");
if (!(hwcap & HWCAP_PACA))
putstr("# Bad hardware? Expect problems.\n");
have_bti = true;
} else {
putstr("# HWCAP2_BTI not present\n");
skip_all = 1;
have_bti = false;
}
putstr("# Test binary");

2
tools/testing/selftests/arm64/fp/.gitignore vendored
View File

@ -12,3 +12,5 @@ vlset
za-fork
za-ptrace
za-test
zt-ptrace
zt-test

5
tools/testing/selftests/arm64/fp/Makefile
View File

@ -14,6 +14,8 @@ TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
sve-test \
ssve-test \
za-test \
zt-ptrace \
zt-test \
vlset
TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
@ -41,5 +43,8 @@ $(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
$(OUTPUT)/za-ptrace: za-ptrace.c
$(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
$(CC) -nostdlib $^ -o $@
$(OUTPUT)/zt-ptrace: zt-ptrace.c
$(OUTPUT)/zt-test: zt-test.S $(OUTPUT)/asm-utils.o
$(CC) -nostdlib $^ -o $@
include ../../lib.mk

2
tools/testing/selftests/arm64/fp/assembler.h
View File

@ -57,7 +57,7 @@ endfunction
// Utility macro to print a literal string
// Clobbers x0-x4,x8
.macro puts string
.pushsection .rodata.str1.1, "aMS", 1
.pushsection .rodata.str1.1, "aMS", @progbits, 1
.L__puts_literal\@: .string "\string"
.popsection

1
tools/testing/selftests/arm64/fp/fp-pidbench.S
View File

@ -31,7 +31,6 @@
// Main program entry point
.globl _start
function _start
_start:
puts "Iterations per test: "
mov x20, #10000
lsl x20, x20, #8

34
tools/testing/selftests/arm64/fp/fp-stress.c
View File

@ -370,6 +370,19 @@ static void start_za(struct child_data *child, int vl, int cpu)
ksft_print_msg("Started %s\n", child->name);
}
static void start_zt(struct child_data *child, int cpu)
{
int ret;
ret = asprintf(&child->name, "ZT-%d", cpu);
if (ret == -1)
ksft_exit_fail_msg("asprintf() failed\n");
child_start(child, "./zt-test");
ksft_print_msg("Started %s\n", child->name);
}
static void probe_vls(int vls[], int *vl_count, int set_vl)
{
unsigned int vq;
@ -377,7 +390,7 @@ static void probe_vls(int vls[], int *vl_count, int set_vl)
*vl_count = 0;
for (vq = SVE_VQ_MAX; vq > 0; --vq) {
for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
vl = prctl(set_vl, vq * 16);
if (vl == -1)
ksft_exit_fail_msg("SET_VL failed: %s (%d)\n",
@ -385,6 +398,9 @@ static void probe_vls(int vls[], int *vl_count, int set_vl)
vl &= PR_SVE_VL_LEN_MASK;
if (*vl_count && (vl == vls[*vl_count - 1]))
break;
vq = sve_vq_from_vl(vl);
vls[*vl_count] = vl;
@ -426,6 +442,7 @@ int main(int argc, char **argv)
bool all_children_started = false;
int seen_children;
int sve_vls[MAX_VLS], sme_vls[MAX_VLS];
bool have_sme2;
struct sigaction sa;
while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) {
@ -458,6 +475,13 @@ int main(int argc, char **argv)
sme_vl_count = 0;
}
if (getauxval(AT_HWCAP2) & HWCAP2_SME2) {
tests += cpus;
have_sme2 = true;
} else {
have_sme2 = false;
}
/* Force context switching if we only have FPSIMD */
if (!sve_vl_count && !sme_vl_count)
fpsimd_per_cpu = 2;
@ -468,8 +492,9 @@ int main(int argc, char **argv)
ksft_print_header();
ksft_set_plan(tests);
ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs\n",
cpus, sve_vl_count, sme_vl_count);
ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs, SME2 %s\n",
cpus, sve_vl_count, sme_vl_count,
have_sme2 ? "present" : "absent");
if (timeout > 0)
ksft_print_msg("Will run for %ds\n", timeout);
@ -527,6 +552,9 @@ int main(int argc, char **argv)
start_ssve(&children[num_children++], sme_vls[j], i);
start_za(&children[num_children++], sme_vls[j], i);
}
if (have_sme2)
start_zt(&children[num_children++], i);
}
/*

1
tools/testing/selftests/arm64/fp/fpsimd-test.S
View File

@ -215,7 +215,6 @@ endfunction
// Main program entry point
.globl _start
function _start
_start:
mov x23, #0 // signal count
mov w0, #SIGINT

Some files were not shown because too many files have changed in this diff Show More